1. Test Modules
  2. Training Characteristics
    1. Input Learning
      1. Gradient Descent
      2. Conjugate Gradient Descent
      3. Limited-Memory BFGS
    2. Results
  3. Results

Subreport: Logs for com.simiacryptus.ref.lang.ReferenceCountingBase

Test Modules

Using Seed 6597469675033321472

Training Characteristics

Input Learning

In this apply, we use a network to learn this target input, given it's pre-evaluated output:

TrainingTester.java:332 executed in 0.01 seconds (0.000 gc):

    return RefArrays.stream(RefUtil.addRef(input_target)).flatMap(RefArrays::stream).map(x -> {
      try {
        return x.prettyPrint();
      } finally {
        x.freeRef();
      }
    }).reduce((a, b) -> a + "\n" + b).orElse("");

Returns

    [
    	[ [ 1.032 ], [ 1.556 ], [ -1.516 ], [ -0.608 ], [ -1.028 ], [ -1.616 ], [ -0.768 ], [ 1.108 ] ],
    	[ [ 1.704 ], [ 0.996 ], [ 1.612 ], [ -1.228 ], [ 0.048 ], [ 0.788 ], [ -0.892 ], [ -1.856 ] ],
    	[ [ 1.876 ], [ 1.512 ], [ 0.08 ], [ 0.148 ], [ -0.384 ], [ -0.032 ], [ -0.804 ], [ 1.368 ] ],
    	[ [ -1.72 ], [ 0.636 ], [ -0.128 ], [ 1.62 ], [ -1.572 ], [ 1.912 ], [ -0.176 ], [ 0.048 ] ],
    	[ [ -0.712 ], [ -0.384 ], [ -0.068 ], [ -0.408 ], [ 1.764 ], [ 0.496 ], [ 1.048 ], [ -1.424 ] ],
    	[ [ -1.688 ], [ -0.852 ], [ 1.652 ], [ -0.804 ], [ 0.7 ], [ 0.028 ], [ 0.3 ], [ -0.464 ] ],
    	[ [ 1.208 ], [ 1.64 ], [ 0.092 ], [ -1.492 ], [ 1.524 ], [ 1.356 ], [ -0.876 ], [ -0.012 ] ],
    	[ [ -1.832 ], [ -1.54 ], [ 1.556 ], [ -0.556 ], [ 0.392 ], [ -1.476 ], [ -0.636 ], [ 1.552 ] ]
    ]
    [
    	[ [ -0.608 ], [ 0.08 ], [ -1.572 ], [ -1.72 ], [ 0.392 ], [ 1.524 ], [ 1.208 ], [ -1.492 ] ],
    	[ [ -0.876 ], [ -1.476 ], [ -0.068 ], [ 1.032 ], [ -0.032 ], [ -1.856 ], [ 0.636 ], [ -1.228 ] ],
    	[ [ 0.048 ], [ -0.804 ], [ 1.556 ], [ 0.7 ], [ 0.496 ], [ -0.408 ], [ -0.176 ], [ -1.832 ] ],
    	[ [ 0.3 ], [ -0.852 ], [ 1.512 ], [ 1.356 ], [ -0.128 ], [ 1.764 ], [ 1.652 ], [ 0.996 ] ],
    	[ [ -0.712 ], [ -1.54 ], [ -0.892 ], [ 0.092 ], [ 1.552 ], [ 1.704 ], [ -0.012 ], [ -1.028 ] ],
    	[ [ -0.768 ], [ 1.368 ], [ 0.028 ], [ -0.556 ], [ -1.616 ], [ -0.636 ], [ 0.148 ], [ 1.048 ] ],
    	[ [ 1.912 ], [ -0.464 ], [ 1.876 ], [ -1.516 ], [ -1.424 ], [ -0.384 ], [ -1.688 ], [ 0.048 ] ],
    	[ [ 1.62 ], [ 1.64 ], [ 0.788 ], [ -0.384 ], [ 1.108 ], [ -0.804 ], [ 1.556 ], [ 1.612 ] ]
    ]
    [
    	[ [ 0.996 ], [ -0.068 ], [ -0.384 ], [ -1.028 ], [ 1.764 ], [ 1.108 ], [ -0.032 ], [ 1.612 ] ],
    	[ [ 1.524 ], [ 0.028 ], [ -1.572 ], [ -0.876 ], [ 1.048 ], [ -1.72 ], [ -1.516 ], [ -0.804 ] ],
    	[ [ 0.7 ], [ 0.048 ], [ 1.556 ], [ -0.384 ], [ -0.804 ], [ -0.768 ], [ -0.608 ], [ -1.832 ] ],
    	[ [ -0.556 ], [ 1.512 ], [ -0.408 ], [ -1.228 ], [ 0.788 ], [ -1.54 ], [ -1.476 ], [ -0.176 ] ],
    	[ [ -0.012 ], [ 1.704 ], [ 1.032 ], [ 1.208 ], [ 0.092 ], [ 0.496 ], [ -1.616 ], [ -1.492 ] ],
    	[ [ 1.64 ], [ -0.128 ], [ 1.652 ], [ -0.464 ], [ -0.852 ], [ 1.552 ], [ 1.62 ], [ 1.912 ] ],
    	[ [ 1.876 ], [ -0.636 ], [ -1.856 ], [ -0.712 ], [ 0.392 ], [ 0.048 ], [ 1.356 ], [ 1.556 ] ],
    	[ [ 0.3 ], [ -0.892 ], [ 0.636 ], [ -1.688 ], [ 0.08 ], [ 1.368 ], [ 0.148 ], [ -1.424 ] ]
    ]
    [
    	[ [ -0.804 ], [ -1.72 ], [ 1.048 ], [ -0.384 ], [ 0.092 ], [ 0.636 ], [ 0.496 ], [ 0.996 ] ],
    	[ [ -0.892 ], [ -0.852 ], [ 1.356 ], [ -0.128 ], [ -0.768 ], [ 1.652 ], [ -0.176 ], [ 1.556 ] ],
    	[ [ -1.028 ], [ 1.108 ], [ -1.832 ], [ 1.764 ], [ 1.64 ], [ 0.048 ], [ -0.636 ], [ 0.392 ] ],
    	[ [ -0.556 ], [ 1.552 ], [ 1.524 ], [ 1.556 ], [ 1.512 ], [ 1.876 ], [ 1.368 ], [ -1.516 ] ],
    	[ [ -0.012 ], [ 1.612 ], [ 1.704 ], [ 0.7 ], [ -1.476 ], [ 0.788 ], [ -0.384 ], [ -1.492 ] ],
    	[ [ -0.876 ], [ 0.3 ], [ 0.148 ], [ -0.032 ], [ 1.62 ], [ -0.408 ], [ -1.688 ], [ -0.804 ] ],
    	[ [ -1.54 ], [ -1.856 ], [ -0.068 ], [ 0.028 ], [ 0.08 ], [ -0.464 ], [ -0.712 ], [ -1.424 ] ],
    	[ [ 0.048 ], [ -1.616 ], [ 1.032 ], [ -0.608 ], [ -1.572 ], [ 1.208 ], [ -1.228 ], [ 1.912 ] ]
    ]
    [
    	[ [ 0.496 ], [ -1.616 ], [ 1.556 ], [ -0.176 ], [ -0.556 ], [ 0.048 ], [ 0.08 ], [ 1.764 ] ],
    	[ [ -1.72 ], [ 1.704 ], [ -0.464 ], [ -1.856 ], [ 0.3 ], [ 1.512 ], [ 0.996 ], [ 0.788 ] ],
    	[ [ -0.768 ], [ -0.892 ], [ 1.62 ], [ -1.688 ], [ 1.032 ], [ -1.228 ], [ -0.384 ], [ -1.476 ] ],
    	[ [ -1.516 ], [ -1.424 ], [ 1.108 ], [ 1.876 ], [ 1.356 ], [ -0.608 ], [ 1.652 ], [ -0.804 ] ],
    	[ [ 1.912 ], [ -0.712 ], [ -0.876 ], [ 1.208 ], [ -0.384 ], [ -0.408 ], [ 1.368 ], [ -0.068 ] ],
    	[ [ 1.556 ], [ -0.012 ], [ -0.128 ], [ -0.852 ], [ 0.636 ], [ 0.092 ], [ -1.832 ], [ -1.028 ] ],
    	[ [ -1.572 ], [ -1.492 ], [ 1.552 ], [ 0.148 ], [ -0.636 ], [ 1.612 ], [ 1.524 ], [ 0.392 ] ],
    	[ [ -0.032 ], [ -0.804 ], [ 0.048 ], [ 1.64 ], [ -1.54 ], [ 1.048 ], [ 0.7 ], [ 0.028 ] ]
    ]

Gradient Descent

First, we train using basic gradient descent method apply weak line search conditions.

TrainingTester.java:480 executed in 0.90 seconds (0.000 gc):

    IterativeTrainer iterativeTrainer = new IterativeTrainer(trainable.addRef());
    try {
      iterativeTrainer.setLineSearchFactory(label -> new ArmijoWolfeSearch());
      iterativeTrainer.setOrientation(new GradientDescent());
      iterativeTrainer.setMonitor(TrainingTester.getMonitor(history));
      iterativeTrainer.setTimeout(30, TimeUnit.SECONDS);
      iterativeTrainer.setMaxIterations(250);
      iterativeTrainer.setTerminateThreshold(0);
      return iterativeTrainer.run();
    } finally {
      iterativeTrainer.freeRef();
    }
Logging
Reset training subject: 3478291897514
BACKPROP_AGG_SIZE = 3
THREADS = 64
SINGLE_THREADED = false
Initialized CoreSettings = {
"backpropAggregationSize" : 3,
"jvmThreads" : 64,
"singleThreaded" : false
}
Reset training subject: 3478325002411
Constructing line search parameters: GD
th(0)=49.64094847998344;dx=-4.7219968000000005E23
New Minimum: 49.64094847998344 > 0.009120779343008902
Armijo: th(2.154434690031884)=0.009120779343008902; dx=-4.721996800114729E11 evalInputDelta=49.631827700640436
Armijo: th(1.077217345015942)=0.010135458609824616; dx=-4.7219968001147296E11 evalInputDelta=49.63081302137362
Armijo: th(0.3590724483386473)=0.4259691461328341; dx=-4.721996800118232E11 evalInputDelta=49.21497933385061
Armijo: th(0.08976811208466183)=2.3986401115716385; dx=-4.721996800202578E11 evalInputDelta=47.242308368411805
Armijo: th(0.017953622416932366)=3.982287590882989; dx=-4.7219968003989307E11 evalInputDelta=45.65866088910045
Armijo: th(0.002992270402822061)=4.607323630419904; dx=-4.721996800560389E11 evalInputDelta=45.03362484956354
Armijo: th(4.2746720040315154E-4)=4.74412255306246; dx=-4.721996800608158E11 evalInputDelta=44.89682592692098
Armijo: th(5.343340005039394E-5)=4.765143076799577; dx=-4.721996800616021E11 evalInputDelta=44.87580540318387
Armijo: th(5.9370444500437714E-6)=4.767833539839756; dx=-4.7219968006170386E11 evalInputDelta=44.87311494014369
Armijo: th(5.937044450043771E-7)=4.768136519522634; dx=-4.7219968006171533E11 evalInputDelta=44.87281196046081
Armijo: th(5.397313136403428E-8)=4.7681671269394; dx=-4.7219968006171643E11 evalInputDelta=44.87278135304404
Armijo: th(4.4977609470028565E-9)=4.768169932650567; dx=-4.7219968006171655E11 evalInputDelta=44.87277854733288
Armijo: th(3.4598161130791205E-10)=4.768170168095099; dx=-4.7219968006171655E11 evalInputDelta=44.87277831188835
Armijo: th(2.4712972236279432E-11)=4.768170186314023; dx=-4.7219968006171655E11 evalInputDelta=44.87277829366942
Armijo: th(1.6475314824186289E-12)=14.399398945397422; dx=-9.144576000100707E22 evalInputDelta=35.24154953458602
Armijo: th(1.029707176511643E-13)=29.869907150553; dx=-2.1156736007007404E23 evalInputDelta=19.771041329430442
Armijo: th(6.057101038303783E-15)=49.6409484799831; dx=-4.721996800000001E23 evalInputDelta=3.410605131648481E-13
MIN ALPHA (3.3650561323909904E-16): th(2.154434690031884)=0.009120779343008902
Fitness changed from 49.64094847998344 to 0.009120779343008902
Iteration 1 complete. Error: 0.009120779343008902 Total: 0.3011; Orientation: 0.0032; Line Search: 0.2439
th(0)=0.009120779343008902;dx=-6.607997970683689
New Minimum: 0.009120779343008902 > 0.0091207793430089
WOLFE (weak): th(2.154434690031884E-15)=0.0091207793430089; dx=-6.607997970683689 evalInputDelta=1.734723475976807E-18
WOLFE (weak): th(4.308869380063768E-15)=0.0091207793430089; dx=-6.607997970683689 evalInputDelta=1.734723475976807E-18
New Minimum: 0.0091207793430089 > 0.009120779343008893
WOLFE (weak): th(1.2926608140191303E-14)=0.009120779343008893; dx=-6.607997970683689 evalInputDelta=8.673617379884035E-18
New Minimum: 0.009120779343008893 > 0.009120779343008862
WOLFE (weak): th(5.1706432560765214E-14)=0.009120779343008862; dx=-6.607997970683689 evalInputDelta=3.9898639947466563E-17
New Minimum: 0.009120779343008862 > 0.009120779343008697
WOLFE (weak): th(2.5853216280382605E-13)=0.009120779343008697; dx=-6.607997970683689 evalInputDelta=2.0469737016526324E-16
New Minimum: 0.009120779343008697 > 0.009120779343007663
WOLFE (weak): th(1.5511929768229563E-12)=0.009120779343007663; dx=-6.607997970683689 evalInputDelta=1.2385925618474403E-15
New Minimum: 0.009120779343007663 > 0.00912077934300021
WOLFE (weak): th(1.0858350837760695E-11)=0.00912077934300021; dx=-6.607997970683688 evalInputDelta=8.690964614643804E-15
New Minimum: 0.00912077934300021 > 0.009120779342939363
WOLFE (weak): th(8.686680670208556E-11)=0.009120779342939363; dx=-6.6079979706836856 evalInputDelta=6.953812525800629E-14
New Minimum: 0.009120779342939363 > 0.009120779342383046
WOLFE (weak): th(7.8180126031877E-10)=0.009120779342383046; dx=-6.607997970683657 evalInputDelta=6.258552703863884E-13
New Minimum: 0.009120779342383046 > 0.009120779336750342
WOLFE (weak): th(7.818012603187701E-9)=0.009120779336750342; dx=-6.607997970683376 evalInputDelta=6.258559642757788E-12
New Minimum: 0.009120779336750342 > 0.009120779274164754
WOLFE (weak): th(8.599813863506471E-8)=0.009120779274164754; dx=-6.607997970680245 evalInputDelta=6.884414739671829E-11
New Minimum: 0.009120779274164754 > 0.00912077851687914
WOLFE (weak): th(1.0319776636207765E-6)=0.00912077851687914; dx=-6.607997970642355 evalInputDelta=8.261297618217256E-10
New Minimum: 0.00912077851687914 > 0.009120768603325306
WOLFE (weak): th(1.3415709627070094E-5)=0.009120768603325306; dx=-6.607997970146348 evalInputDelta=1.0739683595564764E-8
New Minimum: 0.009120768603325306 > 0.00912062898809456
WOLFE (weak): th(1.878199347789813E-4)=0.00912062898809456; dx=-6.607997963160992 evalInputDelta=1.5035491434181592E-7
New Minimum: 0.00912062898809456 > 0.009118524167636137
WOLFE (weak): th(0.0028172990216847197)=0.009118524167636137; dx=-6.607997857858073 evalInputDelta=2.2551753727645396E-6
New Minimum: 0.009118524167636137 > 0.009084734625200241
WOLFE (weak): th(0.045076784346955515)=0.009084734625200241; dx=-6.607996169282133 evalInputDelta=3.6044717808660434E-5
New Minimum: 0.009084734625200241 > 0.008518796268298294
WOLFE (weak): th(0.7663053338982437)=0.008518796268298294; dx=-6.607968411123988 evalInputDelta=6.019830747106079E-4
New Minimum: 0.008518796268298294 > 7.238703897422067E-4
WOLFE (weak): th(13.793496010168386)=7.238703897422067E-4; dx=-6.6076710897160265 evalInputDelta=0.008396908953266695
New Minimum: 7.238703897422067E-4 > 0.0
WOLFE (weak): th(262.07642419319933)=0.0; dx=-6.60765013841509 evalInputDelta=0.009120779343008902
Armijo: th(5241.528483863986)=0.0; dx=-6.60765013841509 evalInputDelta=0.009120779343008902
Armijo: th(2751.802454028593)=0.0; dx=-6.60765013841509 evalInputDelta=0.009120779343008902
Armijo: th(1506.939439110896)=0.0; dx=-6.60765013841509 evalInputDelta=0.009120779343008902
WOLFE (weak): th(884.5079316520477)=0.0; dx=-6.60765013841509 evalInputDelta=0.009120779343008902
WOLFE (weak): th(1195.7236853814718)=0.0; dx=-6.60765013841509 evalInputDelta=0.009120779343008902
WOLFE (weak): th(1351.331562246184)=0.0; dx=-6.60765013841509 evalInputDelta=0.009120779343008902
Armijo: th(1429.13550067854)=0.0; dx=-6.60765013841509 evalInputDelta=0.009120779343008902
Armijo: th(1390.233531462362)=0.0; dx=-6.60765013841509 evalInputDelta=0.009120779343008902
WOLFE (weak): th(1370.7825468542728)=0.0; dx=-6.60765013841509 evalInputDelta=0.009120779343008902
Armijo: th(1380.5080391583174)=0.0; dx=-6.60765013841509 evalInputDelta=0.009120779343008902
mu ~= nu (1370.7825468542728): th(262.07642419319933)=0.0
Fitness changed from 0.009120779343008902 to 0.0
Iteration 2 complete. Error: 0.0 Total: 0.1836; Orientation: 0.0050; Line Search: 0.1693
th(0)=0.0;dx=-6.6074534400000005
Armijo: th(2963.737940431837)=0.0; dx=-6.6074534400000005 evalInputDelta=0.0
Armijo: th(1481.8689702159186)=0.0; dx=-6.6074534400000005 evalInputDelta=0.0
Armijo: th(493.9563234053062)=0.0; dx=-6.6074534400000005 evalInputDelta=0.0
Armijo: th(123.48908085132655)=0.0; dx=-6.6074534400000005 evalInputDelta=0.0
Armijo: th(24.69781617026531)=0.0; dx=-6.6074534400000005 evalInputDelta=0.0
Armijo: th(4.116302695044218)=0.0; dx=-6.6074534400000005 evalInputDelta=0.0
Armijo: th(0.588043242149174)=0.0; dx=-6.6074534400000005 evalInputDelta=0.0
Armijo: th(0.07350540526864675)=0.0; dx=-6.6074534400000005 evalInputDelta=0.0
Armijo: th(0.008167267252071862)=0.0; dx=-6.6074534400000005 evalInputDelta=0.0
Armijo: th(8.167267252071862E-4)=0.0; dx=-6.6074534400000005 evalInputDelta=0.0
Armijo: th(7.42478841097442E-5)=0.0; dx=-6.6074534400000005 evalInputDelta=0.0
Armijo: th(6.187323675812017E-6)=0.0; dx=-6.6074534400000005 evalInputDelta=0.0
Armijo: th(4.7594797506246284E-7)=0.0; dx=-6.6074534400000005 evalInputDelta=0.0
Armijo: th(3.399628393303306E-8)=0.0; dx=-6.6074534400000005 evalInputDelta=0.0
Armijo: th(2.2664189288688707E-9)=0.0; dx=-6.6074534400000005 evalInputDelta=0.0
Armijo: th(1.4165118305430442E-10)=0.0; dx=-6.6074534400000005 evalInputDelta=0.0
Armijo: th(8.332422532606143E-12)=0.0; dx=-6.6074534400000005 evalInputDelta=0.0
Armijo: th(4.629123629225635E-13)=0.0; dx=-6.6074534400000005 evalInputDelta=0.0
Armijo: th(2.4363808574871766E-14)=0.0; dx=-6.6074534400000005 evalInputDelta=0.0
Armijo: th(1.2181904287435882E-15)=0.0; dx=-6.6074534400000005 evalInputDelta=0.0
MIN ALPHA (5.800906803540897E-17): th(0.0)=0.0
Fitness changed from 0.0 to 0.0
Static Iteration Total: 0.4033; Orientation: 0.0008; Line Search: 0.4003
Iteration 3 failed. Error: 0.0
Previous Error: 0.0 -> 0.0
Optimization terminated 3
Final threshold in iteration 3: 0.0 (> 0.0) after 0.889s (< 30.000s)

Returns

    0.0

Training Converged

Conjugate Gradient Descent

First, we use a conjugate gradient descent method, which converges the fastest for purely linear functions.

TrainingTester.java:452 executed in 0.27 seconds (0.000 gc):

    IterativeTrainer iterativeTrainer = new IterativeTrainer(trainable.addRef());
    try {
      iterativeTrainer.setLineSearchFactory(label -> new QuadraticSearch());
      iterativeTrainer.setOrientation(new GradientDescent());
      iterativeTrainer.setMonitor(TrainingTester.getMonitor(history));
      iterativeTrainer.setTimeout(30, TimeUnit.SECONDS);
      iterativeTrainer.setMaxIterations(250);
      iterativeTrainer.setTerminateThreshold(0);
      return iterativeTrainer.run();
    } finally {
      iterativeTrainer.freeRef();
    }
Logging
Reset training subject: 3479186709814
Reset training subject: 3479189276320
Constructing line search parameters: GD
F(0.0) = LineSearchPoint{point=PointSample{avg=49.64094847998344}, derivative=-4.721996800000001E23}
New Minimum: 49.64094847998344 > 4.768170182044548
F(1.0E-10) = LineSearchPoint{point=PointSample{avg=4.768170182044548}, derivative=-4.7219968006171655E11}, evalInputDelta = -44.87277829793889
New Minimum: 4.768170182044548 > 4.76817014801896
F(7.000000000000001E-10) = LineSearchPoint{point=PointSample{avg=4.76817014801896}, derivative=-4.7219968006171655E11}, evalInputDelta = -44.87277833196448
New Minimum: 4.76817014801896 > 4.76816990983987
F(4.900000000000001E-9) = LineSearchPoint{point=PointSample{avg=4.76816990983987}, derivative=-4.7219968006171655E11}, evalInputDelta = -44.87277857014357
New Minimum: 4.76816990983987 > 4.768168242587302
F(3.430000000000001E-8) = LineSearchPoint{point=PointSample{avg=4.768168242587302}, derivative=-4.721996800617165E11}, evalInputDelta = -44.87278023739614
New Minimum: 4.768168242587302 > 4.768156571871289
F(2.4010000000000004E-7) = LineSearchPoint{point=PointSample{avg=4.768156571871289}, derivative=-4.7219968006171606E11}, evalInputDelta = -44.872791908112156
New Minimum: 4.768156571871289 > 4.768074879405487
F(1.6807000000000003E-6) = LineSearchPoint{point=PointSample{avg=4.768074879405487}, derivative=-4.72199680061713E11}, evalInputDelta = -44.872873600577954
New Minimum: 4.768074879405487 > 4.767503156869334
F(1.1764900000000001E-5) = LineSearchPoint{point=PointSample{avg=4.767503156869334}, derivative=-4.7219968006169135E11}, evalInputDelta = -44.87344532311411
New Minimum: 4.767503156869334 > 4.763507195805818
F(8.235430000000001E-5) = LineSearchPoint{point=PointSample{avg=4.763507195805818}, derivative=-4.721996800615404E11}, evalInputDelta = -44.87744128417762
New Minimum: 4.763507195805818 > 4.735829228839135
F(5.764801000000001E-4) = LineSearchPoint{point=PointSample{avg=4.735829228839135}, derivative=-4.721996800605096E11}, evalInputDelta = -44.905119251144306
New Minimum: 4.735829228839135 > 4.554982712800439
F(0.004035360700000001) = LineSearchPoint{point=PointSample{avg=4.554982712800439}, derivative=-4.7219968005435486E11}, evalInputDelta = -45.085965767183005
New Minimum: 4.554982712800439 > 3.656222218340004
F(0.028247524900000005) = LineSearchPoint{point=PointSample{avg=3.656222218340004}, derivative=-4.721996800340281E11}, evalInputDelta = -45.98472626164344
New Minimum: 3.656222218340004 > 1.1768403222501573
F(0.19773267430000002) = LineSearchPoint{point=PointSample{avg=1.1768403222501573}, derivative=-4.7219968001383167E11}, evalInputDelta = -48.464108157733286
New Minimum: 1.1768403222501573 > 0.00983975086822087
F(1.3841287201) = LineSearchPoint{point=PointSample{avg=0.00983975086822087}, derivative=-4.721996800114729E11}, evalInputDelta = -49.63110872911522
New Minimum: 0.00983975086822087 > 0.003400299230150326
F(9.688901040700001) = LineSearchPoint{point=PointSample{avg=0.003400299230150326}, derivative=-4.7219968001147266E11}, evalInputDelta = -49.63754818075329
New Minimum: 0.003400299230150326 > 0.0
F(67.8223072849) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-4.7219968001147253E11}, evalInputDelta = -49.64094847998344
F(474.7561509943) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-4.7219968001147253E11}, evalInputDelta = -49.64094847998344
F(3323.2930569601003) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-4.7219968001147253E11}, evalInputDelta = -49.64094847998344
F(23263.0513987207) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-4.7219968001147253E11}, evalInputDelta = -49.64094847998344
F(162841.3597910449) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-4.721996800114725E11}, evalInputDelta = -49.64094847998344
F(1139889.5185373144) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-4.721996800114725E11}, evalInputDelta = -49.64094847998344
F(7979226.6297612) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-4.7219968001147253E11}, evalInputDelta = -49.64094847998344
F(5.58545864083284E7) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-4.7219968001147253E11}, evalInputDelta = -49.64094847998344
F(3.909821048582988E8) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-4.7219968001147253E11}, evalInputDelta = -49.64094847998344
F(2.7368747340080914E9) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-4.721996800114725E11}, evalInputDelta = -49.64094847998344
F(1.915812313805664E10) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-4.7219968001147253E11}, evalInputDelta = -49.64094847998344
0.0 <= 49.64094847998344
F(1.0E10) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-4.7219968001147253E11}, evalInputDelta = -49.64094847998344
Right bracket at 1.0E10
Converged to right
Fitness changed from 49.64094847998344 to 0.0
Iteration 1 complete. Error: 0.0 Total: 0.1346; Orientation: 0.0010; Line Search: 0.1258
F(0.0) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-6.6074534400000005}
F(1.0E10) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-6.6074534400000005}, evalInputDelta = 0.0
0.0 <= 0.0
F(5.0E9) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-6.6074534400000005}, evalInputDelta = 0.0
Right bracket at 5.0E9
F(2.5E9) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-6.6074534400000005}, evalInputDelta = 0.0
Right bracket at 2.5E9
F(1.25E9) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-6.6074534400000005}, evalInputDelta = 0.0
Right bracket at 1.25E9
F(6.25E8) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-6.6074534400000005}, evalInputDelta = 0.0
Right bracket at 6.25E8
F(3.125E8) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-6.6074534400000005}, evalInputDelta = 0.0
Right bracket at 3.125E8
F(1.5625E8) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-6.6074534400000005}, evalInputDelta = 0.0
Right bracket at 1.5625E8
F(7.8125E7) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-6.6074534400000005}, evalInputDelta = 0.0
Right bracket at 7.8125E7
F(3.90625E7) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-6.6074534400000005}, evalInputDelta = 0.0
Right bracket at 3.90625E7
F(1.953125E7) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-6.6074534400000005}, evalInputDelta = 0.0
Right bracket at 1.953125E7
F(9765625.0) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-6.6074534400000005}, evalInputDelta = 0.0
Right bracket at 9765625.0
F(4882812.5) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-6.6074534400000005}, evalInputDelta = 0.0
Right bracket at 4882812.5
F(2441406.25) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-6.6074534400000005}, evalInputDelta = 0.0
Loops = 12
Fitness changed from 0.0 to 0.0
Static Iteration Total: 0.1378; Orientation: 0.0008; Line Search: 0.1348
Iteration 2 failed. Error: 0.0
Previous Error: 0.0 -> 0.0
Optimization terminated 2
Final threshold in iteration 2: 0.0 (> 0.0) after 0.273s (< 30.000s)

Returns

    0.0

Training Converged

Limited-Memory BFGS

Next, we apply the same optimization using L-BFGS, which is nearly ideal for purely second-order or quadratic functions.

TrainingTester.java:509 executed in 10.56 seconds (0.045 gc):

    IterativeTrainer iterativeTrainer = new IterativeTrainer(trainable.addRef());
    try {
      iterativeTrainer.setLineSearchFactory(label -> new ArmijoWolfeSearch());
      iterativeTrainer.setOrientation(new LBFGS());
      iterativeTrainer.setMonitor(TrainingTester.getMonitor(history));
      iterativeTrainer.setTimeout(30, TimeUnit.SECONDS);
      iterativeTrainer.setIterationsPerSample(100);
      iterativeTrainer.setMaxIterations(250);
      iterativeTrainer.setTerminateThreshold(0);
      return iterativeTrainer.run();
    } finally {
      iterativeTrainer.freeRef();
    }
Logging
Reset training subject: 3479465237830
Reset training subject: 3479467814519
Adding measurement 5e5227ca to history. Total: 0
LBFGS Accumulation History: 1 points
Constructing line search parameters: GD
Non-optimal measurement 49.64094847998344 < 49.64094847998344. Total: 1
th(0)=49.64094847998344;dx=-4.721996800000001E23
Adding measurement 3e7f29b4 to history. Total: 1
New Minimum: 49.64094847998344 > 0.009120779343008902
Armijo: th(2.154434690031884)=0.009120779343008902; dx=-4.721996800114729E11 evalInputDelta=49.631827700640436
Non-optimal measurement 0.010135458609824616 < 0.009120779343008902. Total: 2
Armijo: th(1.077217345015942)=0.010135458609824616; dx=-4.7219968001147296E11 evalInputDelta=49.63081302137362
Non-optimal measurement 0.4259691461328341 < 0.009120779343008902. Total: 2
Armijo: th(0.3590724483386473)=0.4259691461328341; dx=-4.721996800118232E11 evalInputDelta=49.21497933385061
Non-optimal measurement 2.3986401115716385 < 0.009120779343008902. Total: 2
Armijo: th(0.08976811208466183)=2.3986401115716385; dx=-4.721996800202578E11 evalInputDelta=47.242308368411805
Non-optimal measurement 3.982287590882989 < 0.009120779343008902. Total: 2
Armijo: th(0.017953622416932366)=3.982287590882989; dx=-4.7219968003989307E11 evalInputDelta=45.65866088910045
Non-optimal measurement 4.607323630419904 < 0.009120779343008902. Total: 2
Armijo: th(0.002992270402822061)=4.607323630419904; dx=-4.721996800560389E11 evalInputDelta=45.03362484956354
Non-optimal measurement 4.74412255306246 < 0.009120779343008902. Total: 2
Armijo: th(4.2746720040315154E-4)=4.74412255306246; dx=-4.721996800608158E11 evalInputDelta=44.89682592692098
Non-optimal measurement 4.765143076799577 < 0.009120779343008902. Total: 2
Armijo: th(5.343340005039394E-5)=4.765143076799577; dx=-4.721996800616021E11 evalInputDelta=44.87580540318387
Non-optimal measurement 4.767833539839756 < 0.009120779343008902. Total: 2
Armijo: th(5.9370444500437714E-6)=4.767833539839756; dx=-4.7219968006170386E11 evalInputDelta=44.87311494014369
Non-optimal measurement 4.768136519522634 < 0.009120779343008902. Total: 2
Armijo: th(5.937044450043771E-7)=4.768136519522634; dx=-4.7219968006171533E11 evalInputDelta=44.87281196046081
Non-optimal measurement 4.7681671269394 < 0.009120779343008902. Total: 2
Armijo: th(5.397313136403428E-8)=4.7681671269394; dx=-4.7219968006171643E11 evalInputDelta=44.87278135304404
Non-optimal measurement 4.768169932650567 < 0.009120779343008902. Total: 2
Armijo: th(4.4977609470028565E-9)=4.768169932650567; dx=-4.7219968006171655E11 evalInputDelta=44.87277854733288
Non-optimal measurement 4.768170168095099 < 0.009120779343008902. Total: 2
Armijo: th(3.4598161130791205E-10)=4.768170168095099; dx=-4.7219968006171655E11 evalInputDelta=44.87277831188835
Non-optimal measurement 4.768170186314023 < 0.009120779343008902. Total: 2
Armijo: th(2.4712972236279432E-11)=4.768170186314023; dx=-4.7219968006171655E11 evalInputDelta=44.87277829366942
Non-optimal measurement 14.399398945397422 < 0.009120779343008902. Total: 2
Armijo: th(1.6475314824186289E-12)=14.399398945397422; dx=-9.144576000100707E22 evalInputDelta=35.24154953458602
Non-optimal measurement 29.869907150553 < 0.009120779343008902. Total: 2
Armijo: th(1.029707176511643E-13)=29.869907150553; dx=-2.1156736007007404E23 evalInputDelta=19.771041329430442
Non-optimal measurement 49.6409484799831 < 0.009120779343008902. Total: 2
Armijo: th(6.057101038303783E-15)=49.6409484799831; dx=-4.721996800000001E23 evalInputDelta=3.410605131648481E-13
Non-optimal measurement 0.009120779343008902 < 0.009120779343008902. Total: 2
MIN ALPHA (3.3650561323909904E-16): th(2.154434690031884)=0.009120779343008902
Fitness changed from 49.64094847998344 to 0.009120779343008902
Iteration 1 complete. Error: 0.009120779343008902 Total: 0.1128; Orientation: 0.0057; Line Search: 0.0992
Non-optimal measurement 0.009120779343008902 < 0.009120779343008902. Total: 2
LBFGS Accumulation History: 2 points
Non-optimal measurement 0.009120779343008902 < 0.009120779343008902. Total: 2
th(0)=0.009120779343008902;dx=-6.607997970683689
Adding measurement 37468a49 to history. Total: 2
New Minimum: 0.009120779343008902 > 0.0091207793430089
WOLFE (weak): th(2.154434690031884E-15)=0.0091207793430089; dx=-6.607997970683689 evalInputDelta=1.734723475976807E-18
Non-optimal measurement 0.0091207793430089 < 0.0091207793430089. Total: 3
WOLFE (weak): th(4.308869380063768E-15)=0.0091207793430089; dx=-6.607997970683689 evalInputDelta=1.734723475976807E-18
Adding measurement 533f3aea to history. Total: 3
New Minimum: 0.0091207793430089 > 0.009120779343008893
WOLFE (weak): th(1.2926608140191303E-14)=0.009120779343008893; dx=-6.607997970683689 evalInputDelta=8.673617379884035E-18
Adding measurement 329e26c2 to history. Total: 4
New Minimum: 0.009120779343008893 > 0.009120779343008862
WOLFE (weak): th(5.1706432560765214E-14)=0.009120779343008862; dx=-6.607997970683689 evalInputDelta=3.9898639947466563E-17
Adding measurement 2675d73a to history. Total: 5
New Minimum: 0.009120779343008862 > 0.009120779343008697
WOLFE (weak): th(2.5853216280382605E-13)=0.009120779343008697; dx=-6.607997970683689 evalInputDelta=2.0469737016526324E-16
Adding measurement 187f947f to history. Total: 6
New Minimum: 0.009120779343008697 > 0.009120779343007663
WOLFE (weak): th(1.5511929768229563E-12)=0.009120779343007663; dx=-6.607997970683689 evalInputDelta=1.2385925618474403E-15
Adding measurement 68598002 to history. Total: 7
New Minimum: 0.009120779343007663 > 0.00912077934300021
WOLFE (weak): th(1.0858350837760695E-11)=0.00912077934300021; dx=-6.607997970683688 evalInputDelta=8.690964614643804E-15
Adding measurement 48c57c66 to history. Total: 8
New Minimum: 0.00912077934300021 > 0.009120779342939363
WOLFE (weak): th(8.686680670208556E-11)=0.009120779342939363; dx=-6.6079979706836856 evalInputDelta=6.953812525800629E-14
Adding measurement 3a5b2743 to history. Total: 9
New Minimum: 0.009120779342939363 > 0.009120779342383046
WOLFE (weak): th(7.8180126031877E-10)=0.009120779342383046; dx=-6.607997970683657 evalInputDelta=6.258552703863884E-13
Adding measurement 7f6c6d45 to history. Total: 10
New Minimum: 0.009120779342383046 > 0.009120779336750342
WOLFE (weak): th(7.818012603187701E-9)=0.009120779336750342; dx=-6.607997970683376 evalInputDelta=6.258559642757788E-12
Adding measurement 221eeafb to history. Total: 11
New Minimum: 0.009120779336750342 > 0.009120779274164754
WOLFE (weak): th(8.599813863506471E-8)=0.009120779274164754; dx=-6.607997970680245 evalInputDelta=6.884414739671829E-11
Adding measurement 1f37a9f9 to history. Total: 12
New Minimum: 0.009120779274164754 > 0.00912077851687914
WOLFE (weak): th(1.0319776636207765E-6)=0.00912077851687914; dx=-6.607997970642355 evalInputDelta=8.261297618217256E-10
Adding measurement 3fccda1b to history. Total: 13
New Minimum: 0.00912077851687914 > 0.009120768603325306
WOLFE (weak): th(1.3415709627070094E-5)=0.009120768603325306; dx=-6.607997970146348 evalInputDelta=1.0739683595564764E-8
Adding measurement 473e3e62 to history. Total: 14
New Minimum: 0.009120768603325306 > 0.00912062898809456
WOLFE (weak): th(1.878199347789813E-4)=0.00912062898809456; dx=-6.607997963160992 evalInputDelta=1.5035491434181592E-7
Adding measurement 203e5bd7 to history. Total: 15
New Minimum: 0.00912062898809456 > 0.009118524167636137
WOLFE (weak): th(0.0028172990216847197)=0.009118524167636137; dx=-6.607997857858073 evalInputDelta=2.2551753727645396E-6
Adding measurement 6babaff1 to history. Total: 16
New Minimum: 0.009118524167636137 > 0.009084734625200241
WOLFE (weak): th(0.045076784346955515)=0.009084734625200241; dx=-6.607996169282133 evalInputDelta=3.6044717808660434E-5
Adding measurement 3522e6ad to history. Total: 17
New Minimum: 0.009084734625200241 > 0.008518796268298294
WOLFE (weak): th(0.7663053338982437)=0.008518796268298294; dx=-6.607968411123988 evalInputDelta=6.019830747106079E-4
Adding measurement 7f1f84a4 to history. Total: 18
New Minimum: 0.008518796268298294 > 7.238703897422067E-4
WOLFE (weak): th(13.793496010168386)=7.238703897422067E-4; dx=-6.6076710897160265 evalInputDelta=0.008396908953266695
Adding measurement 696c78f5 to history. Total: 19
New Minimum: 7.

...skipping 8589 bytes...

b4e69-4b46-4cb5-b4fa-4a0b9a13de40 = 1.000/1.000e+00, b5e73516-8589-4867-8ff3-556d8d3e8dd5 = 1.000/1.000e+00, 4cac9f92-72e8-47a5-80af-dc0fcac9444f = 1.000/1.000e+00, 995d4f5d-7639-4eb6-9aa5-86625400d9b7 = 1.000/1.000e+00, cbed20ab-31de-4cbb-b089-35527bc4bd6c = 1.000/1.000e+00]
Orientation rejected. Popping history element from 0.0, 7.238703897422067E-4, 0.008518796268298294, 0.009084734625200241, 0.009118524167636137, 0.00912062898809456, 0.009120768603325306, 0.00912077851687914, 0.009120779274164754, 0.009120779336750342, 0.009120779342383046
Rejected: LBFGS Orientation magnitude: 7.969e+05, gradient 2.570e+00, dot -0.993; [b5e73516-8589-4867-8ff3-556d8d3e8dd5 = 1.000/1.000e+00, 995d4f5d-7639-4eb6-9aa5-86625400d9b7 = 1.000/1.000e+00, cbed20ab-31de-4cbb-b089-35527bc4bd6c = 1.000/1.000e+00, 4cac9f92-72e8-47a5-80af-dc0fcac9444f = 1.000/1.000e+00, 0dfb4e69-4b46-4cb5-b4fa-4a0b9a13de40 = 1.000/1.000e+00]
Orientation rejected. Popping history element from 0.0, 7.238703897422067E-4, 0.008518796268298294, 0.009084734625200241, 0.009118524167636137, 0.00912062898809456, 0.009120768603325306, 0.00912077851687914, 0.009120779274164754, 0.009120779336750342
Rejected: LBFGS Orientation magnitude: 7.969e+05, gradient 2.570e+00, dot -0.993; [cbed20ab-31de-4cbb-b089-35527bc4bd6c = 1.000/1.000e+00, b5e73516-8589-4867-8ff3-556d8d3e8dd5 = 1.000/1.000e+00, 995d4f5d-7639-4eb6-9aa5-86625400d9b7 = 1.000/1.000e+00, 4cac9f92-72e8-47a5-80af-dc0fcac9444f = 1.000/1.000e+00, 0dfb4e69-4b46-4cb5-b4fa-4a0b9a13de40 = 1.000/1.000e+00]
Orientation rejected. Popping history element from 0.0, 7.238703897422067E-4, 0.008518796268298294, 0.009084734625200241, 0.009118524167636137, 0.00912062898809456, 0.009120768603325306, 0.00912077851687914, 0.009120779274164754
Rejected: LBFGS Orientation magnitude: 7.969e+05, gradient 2.570e+00, dot -0.993; [b5e73516-8589-4867-8ff3-556d8d3e8dd5 = 1.000/1.000e+00, cbed20ab-31de-4cbb-b089-35527bc4bd6c = 1.000/1.000e+00, 4cac9f92-72e8-47a5-80af-dc0fcac9444f = 1.000/1.000e+00, 0dfb4e69-4b46-4cb5-b4fa-4a0b9a13de40 = 1.000/1.000e+00, 995d4f5d-7639-4eb6-9aa5-86625400d9b7 = 1.000/1.000e+00]
Orientation rejected. Popping history element from 0.0, 7.238703897422067E-4, 0.008518796268298294, 0.009084734625200241, 0.009118524167636137, 0.00912062898809456, 0.009120768603325306, 0.00912077851687914
Rejected: LBFGS Orientation magnitude: 8.370e+05, gradient 2.570e+00, dot -0.992; [cbed20ab-31de-4cbb-b089-35527bc4bd6c = 1.000/1.000e+00, 995d4f5d-7639-4eb6-9aa5-86625400d9b7 = 1.000/1.000e+00, 0dfb4e69-4b46-4cb5-b4fa-4a0b9a13de40 = 1.000/1.000e+00, 4cac9f92-72e8-47a5-80af-dc0fcac9444f = 1.000/1.000e+00, b5e73516-8589-4867-8ff3-556d8d3e8dd5 = 1.000/1.000e+00]
Orientation rejected. Popping history element from 0.0, 7.238703897422067E-4, 0.008518796268298294, 0.009084734625200241, 0.009118524167636137, 0.00912062898809456, 0.009120768603325306
Rejected: LBFGS Orientation magnitude: 8.489e+05, gradient 2.570e+00, dot -1.000; [cbed20ab-31de-4cbb-b089-35527bc4bd6c = 1.000/1.000e+00, 4cac9f92-72e8-47a5-80af-dc0fcac9444f = 1.000/1.000e+00, b5e73516-8589-4867-8ff3-556d8d3e8dd5 = 1.000/1.000e+00, 995d4f5d-7639-4eb6-9aa5-86625400d9b7 = 1.000/1.000e+00, 0dfb4e69-4b46-4cb5-b4fa-4a0b9a13de40 = 1.000/1.000e+00]
Orientation rejected. Popping history element from 0.0, 7.238703897422067E-4, 0.008518796268298294, 0.009084734625200241, 0.009118524167636137, 0.00912062898809456
Rejected: LBFGS Orientation magnitude: 8.503e+05, gradient 2.570e+00, dot -1.000; [cbed20ab-31de-4cbb-b089-35527bc4bd6c = 1.000/1.000e+00, 0dfb4e69-4b46-4cb5-b4fa-4a0b9a13de40 = 1.000/1.000e+00, 4cac9f92-72e8-47a5-80af-dc0fcac9444f = 1.000/1.000e+00, b5e73516-8589-4867-8ff3-556d8d3e8dd5 = 1.000/1.000e+00, 995d4f5d-7639-4eb6-9aa5-86625400d9b7 = 1.000/1.000e+00]
Orientation rejected. Popping history element from 0.0, 7.238703897422067E-4, 0.008518796268298294, 0.009084734625200241, 0.009118524167636137
Rejected: LBFGS Orientation magnitude: 8.826e+05, gradient 2.570e+00, dot -1.000; [b5e73516-8589-4867-8ff3-556d8d3e8dd5 = 1.000/1.000e+00, 995d4f5d-7639-4eb6-9aa5-86625400d9b7 = 1.000/1.000e+00, cbed20ab-31de-4cbb-b089-35527bc4bd6c = 1.000/1.000e+00, 0dfb4e69-4b46-4cb5-b4fa-4a0b9a13de40 = 1.000/1.000e+00, 4cac9f92-72e8-47a5-80af-dc0fcac9444f = 1.000/1.000e+00]
Orientation rejected. Popping history element from 0.0, 7.238703897422067E-4, 0.008518796268298294, 0.009084734625200241
LBFGS Accumulation History: 3 points
Removed measurement 696c78f5 to history. Total: 19
Removed measurement 7f1f84a4 to history. Total: 18
Removed measurement 3522e6ad to history. Total: 17
Removed measurement 6babaff1 to history. Total: 16
Removed measurement 203e5bd7 to history. Total: 15
Removed measurement 473e3e62 to history. Total: 14
Removed measurement 3fccda1b to history. Total: 13
Removed measurement 1f37a9f9 to history. Total: 12
Removed measurement 221eeafb to history. Total: 11
Removed measurement 7f6c6d45 to history. Total: 10
Removed measurement 3a5b2743 to history. Total: 9
Removed measurement 48c57c66 to history. Total: 8
Removed measurement 68598002 to history. Total: 7
Removed measurement 187f947f to history. Total: 6
Removed measurement 2675d73a to history. Total: 5
Removed measurement 329e26c2 to history. Total: 4
Removed measurement 533f3aea to history. Total: 3
Adding measurement 66322810 to history. Total: 3
th(0)=0.0;dx=-6.6074534400000005
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(2963.737940431837)=0.0; dx=-6.6074534400000005 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(1481.8689702159186)=0.0; dx=-6.6074534400000005 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(493.9563234053062)=0.0; dx=-6.6074534400000005 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(123.48908085132655)=0.0; dx=-6.6074534400000005 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(24.69781617026531)=0.0; dx=-6.6074534400000005 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(4.116302695044218)=0.0; dx=-6.6074534400000005 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(0.588043242149174)=0.0; dx=-6.6074534400000005 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(0.07350540526864675)=0.0; dx=-6.6074534400000005 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(0.008167267252071862)=0.0; dx=-6.6074534400000005 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(8.167267252071862E-4)=0.0; dx=-6.6074534400000005 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(7.42478841097442E-5)=0.0; dx=-6.6074534400000005 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(6.187323675812017E-6)=0.0; dx=-6.6074534400000005 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(4.7594797506246284E-7)=0.0; dx=-6.6074534400000005 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(3.399628393303306E-8)=0.0; dx=-6.6074534400000005 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(2.2664189288688707E-9)=0.0; dx=-6.6074534400000005 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(1.4165118305430442E-10)=0.0; dx=-6.6074534400000005 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(8.332422532606143E-12)=0.0; dx=-6.6074534400000005 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(4.629123629225635E-13)=0.0; dx=-6.6074534400000005 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(2.4363808574871766E-14)=0.0; dx=-6.6074534400000005 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(1.2181904287435882E-15)=0.0; dx=-6.6074534400000005 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
MIN ALPHA (5.800906803540897E-17): th(0.0)=0.0
Fitness changed from 0.0 to 0.0
Static Iteration Total: 10.3122; Orientation: 10.1125; Line Search: 0.1978
Iteration 3 failed. Error: 0.0
Previous Error: 0.0 -> 0.0
Optimization terminated 3
Final threshold in iteration 3: 0.0 (> 0.0) after 10.560s (< 30.000s)

Returns

    0.0

Training Converged

TrainingTester.java:432 executed in 0.10 seconds (0.000 gc):

    return TestUtil.compare(title + " vs Iteration", runs);
Logging
Plotting range=[1.0, -3.039968050936114], [2.0, -1.039968050936114]; valueStats=DoubleSummaryStatistics{count=2, sum=0.018242, min=0.009121, average=0.009121, max=0.009121}
Plotting 2 points for GD
Only 1 points for CjGD
Plotting 2 points for LBFGS

Returns

Result

TrainingTester.java:435 executed in 0.01 seconds (0.000 gc):

    return TestUtil.compareTime(title + " vs Time", runs);
Logging
Plotting range=[0.0, -3.039968050936114], [0.183, -1.039968050936114]; valueStats=DoubleSummaryStatistics{count=2, sum=0.018242, min=0.009121, average=0.009121, max=0.009121}
Plotting 2 points for GD
Only 1 points for CjGD
Plotting 2 points for LBFGS

Returns

Result

Results

TrainingTester.java:255 executed in 0.00 seconds (0.000 gc):

    return grid(inputLearning, modelLearning, completeLearning);

Returns

Result

TrainingTester.java:258 executed in 0.00 seconds (0.000 gc):

    return new ComponentResult(null == inputLearning ? null : inputLearning.value,
        null == modelLearning ? null : modelLearning.value, null == completeLearning ? null : completeLearning.value);

Returns

    {"input":{ "LBFGS": { "type": "Converged", "value": 0.0 }, "CjGD": { "type": "Converged", "value": 0.0 }, "GD": { "type": "Converged", "value": 0.0 } }, "model":null, "complete":null}

LayerTests.java:425 executed in 0.00 seconds (0.000 gc):

    throwException(exceptions.addRef());

Results

detailsresult
{"input":{ "LBFGS": { "type": "Converged", "value": 0.0 }, "CjGD": { "type": "Converged", "value": 0.0 }, "GD": { "type": "Converged", "value": 0.0 } }, "model":null, "complete":null}OK
  {
    "result": "OK",
    "performance": {
      "execution_time": "12.429",
      "gc_time": "0.332"
    },
    "created_on": 1586738066082,
    "file_name": "trainingTest",
    "report": {
      "simpleName": "Basic",
      "canonicalName": "com.simiacryptus.mindseye.layers.java.MaxPoolingLayerTest.Basic",
      "link": "https://github.com/SimiaCryptus/mindseye-java/tree/93db34cedee48c0202777a2b25deddf1dfaf5731/src/test/java/com/simiacryptus/mindseye/layers/java/MaxPoolingLayerTest.java",
      "javaDoc": ""
    },
    "training_analysis": {
      "input": {
        "LBFGS": {
          "type": "Converged",
          "value": 0.0
        },
        "CjGD": {
          "type": "Converged",
          "value": 0.0
        },
        "GD": {
          "type": "Converged",
          "value": 0.0
        }
      }
    },
    "archive": "s3://code.simiacrypt.us/tests/com/simiacryptus/mindseye/layers/java/MaxPoolingLayer/Basic/trainingTest/202004133426",
    "id": "d30dbf3a-fcce-4669-af9f-95beffc62b13",
    "report_type": "Components",
    "display_name": "Comparative Training",
    "target": {
      "simpleName": "MaxPoolingLayer",
      "canonicalName": "com.simiacryptus.mindseye.layers.java.MaxPoolingLayer",
      "link": "https://github.com/SimiaCryptus/mindseye-java/tree/93db34cedee48c0202777a2b25deddf1dfaf5731/src/main/java/com/simiacryptus/mindseye/layers/java/MaxPoolingLayer.java",
      "javaDoc": ""
    }
  }