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 5582557074651444224

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

    [
    	[ [ 1.208 ], [ 1.048 ], [ -0.768 ], [ 1.356 ], [ 0.3 ], [ -0.068 ] ],
    	[ [ -0.608 ], [ 1.032 ], [ -0.384 ], [ 0.636 ], [ 1.108 ], [ 1.612 ] ],
    	[ [ 0.7 ], [ -0.176 ], [ -0.852 ], [ 0.028 ], [ 1.764 ], [ 0.392 ] ],
    	[ [ 1.912 ], [ -1.616 ], [ 0.788 ], [ 0.092 ], [ 1.556 ], [ -0.804 ] ],
    	[ [ -1.688 ], [ 0.496 ], [ -1.72 ], [ 1.556 ], [ 0.08 ], [ 1.524 ] ],
    	[ [ -0.712 ], [ 0.048 ], [ 1.512 ], [ -0.128 ], [ -1.028 ], [ 1.64 ] ]
    ]
    [
    	[ [ 0.7 ], [ 0.092 ], [ -1.72 ], [ -0.852 ], [ 1.64 ], [ -1.028 ] ],
    	[ [ 0.3 ], [ 1.512 ], [ 1.048 ], [ -0.176 ], [ 1.764 ], [ -0.712 ] ],
    	[ [ 1.524 ], [ 0.048 ], [ 1.556 ], [ 0.08 ], [ 1.032 ], [ -0.384 ] ],
    	[ [ 0.496 ], [ 0.392 ], [ 1.612 ], [ 1.912 ], [ 0.028 ], [ -1.688 ] ],
    	[ [ -0.804 ], [ -0.128 ], [ 0.636 ], [ 1.556 ], [ -0.068 ], [ 1.356 ] ],
    	[ [ -0.768 ], [ -0.608 ], [ 1.208 ], [ -1.616 ], [ 1.108 ], [ 0.788 ] ]
    ]
    [
    	[ [ 0.3 ], [ 0.028 ], [ 1.048 ], [ -1.688 ], [ -0.384 ], [ 1.556 ] ],
    	[ [ 1.524 ], [ 1.208 ], [ 0.7 ], [ 1.032 ], [ 0.048 ], [ 0.08 ] ],
    	[ [ 1.764 ], [ -0.852 ], [ -0.804 ], [ 0.392 ], [ 0.636 ], [ -1.616 ] ],
    	[ [ -0.608 ], [ -1.028 ], [ -0.128 ], [ -0.176 ], [ 1.356 ], [ 0.092 ] ],
    	[ [ 1.912 ], [ 1.556 ], [ 1.512 ], [ 1.64 ], [ -1.72 ], [ 1.612 ] ],
    	[ [ -0.068 ], [ -0.712 ], [ 0.788 ], [ 0.496 ], [ 1.108 ], [ -0.768 ] ]
    ]
    [
    	[ [ 0.048 ], [ 0.7 ], [ 1.032 ], [ -0.176 ], [ 1.612 ], [ 0.028 ] ],
    	[ [ 0.496 ], [ -1.72 ], [ 0.636 ], [ 1.764 ], [ 1.108 ], [ -0.852 ] ],
    	[ [ 1.524 ], [ -0.804 ], [ 0.092 ], [ 0.788 ], [ -0.384 ], [ 0.392 ] ],
    	[ [ 0.08 ], [ -1.616 ], [ -0.608 ], [ -1.028 ], [ 1.556 ], [ 1.048 ] ],
    	[ [ 1.208 ], [ 1.512 ], [ 1.556 ], [ 1.912 ], [ -0.712 ], [ 1.356 ] ],
    	[ [ -0.768 ], [ -1.688 ], [ 0.3 ], [ -0.068 ], [ 1.64 ], [ -0.128 ] ]
    ]
    [
    	[ [ 0.092 ], [ -1.028 ], [ 1.556 ], [ 1.208 ], [ -1.616 ], [ 1.612 ] ],
    	[ [ -0.128 ], [ -0.768 ], [ -0.608 ], [ 0.392 ], [ -1.72 ], [ 1.108 ] ],
    	[ [ 1.912 ], [ -0.176 ], [ 0.496 ], [ -0.384 ], [ 0.636 ], [ 0.788 ] ],
    	[ [ 1.048 ], [ 0.3 ], [ 1.64 ], [ 0.028 ], [ 0.048 ], [ -0.712 ] ],
    	[ [ 0.08 ], [ -1.688 ], [ 1.524 ], [ 1.032 ], [ -0.068 ], [ 1.764 ] ],
    	[ [ -0.804 ], [ 1.556 ], [ 1.512 ], [ 0.7 ], [ -0.852 ], [ 1.356 ] ]
    ]

Gradient Descent

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

TrainingTester.java:480 executed in 0.63 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: 1248649387564
BACKPROP_AGG_SIZE = 3
THREADS = 64
SINGLE_THREADED = false
Initialized CoreSettings = {
"backpropAggregationSize" : 3,
"jvmThreads" : 64,
"singleThreaded" : false
}
Reset training subject: 1248679232067
Constructing line search parameters: GD
th(0)=198.87492333195217;dx=-1.82272128E24
New Minimum: 198.87492333195217 > 0.040376148285368174
Armijo: th(2.154434690031884)=0.040376148285368174; dx=-1.8227212800199805E12 evalInputDelta=198.8345471836668
Armijo: th(1.077217345015942)=0.13565768176441656; dx=-1.822721280020022E12 evalInputDelta=198.73926565018775
Armijo: th(0.3590724483386473)=1.5084087331159235; dx=-1.822721280021404E12 evalInputDelta=197.36651459883626
Armijo: th(0.08976811208466183)=5.192915663551141; dx=-1.8227212800380686E12 evalInputDelta=193.68200766840104
Armijo: th(0.017953622416932366)=9.313358984575963; dx=-1.8227212801073335E12 evalInputDelta=189.56156434737622
Armijo: th(0.002992270402822061)=11.517506629001524; dx=-1.8227212802262598E12 evalInputDelta=187.35741670295064
Armijo: th(4.2746720040315154E-4)=12.177732642077945; dx=-1.8227212803022075E12 evalInputDelta=186.69719068987422
Armijo: th(5.343340005039394E-5)=12.293215439192874; dx=-1.8227212803198232E12 evalInputDelta=186.5817078927593
Armijo: th(5.9370444500437714E-6)=12.30836666855716; dx=-1.8227212803222637E12 evalInputDelta=186.566556663395
Armijo: th(5.937044450043771E-7)=12.310078465858734; dx=-1.8227212803225415E12 evalInputDelta=186.56484486609344
Armijo: th(5.397313136403428E-8)=12.310251457231484; dx=-1.8227212803225696E12 evalInputDelta=186.5646718747207
Armijo: th(4.4977609470028565E-9)=12.310267315532547; dx=-1.8227212803225723E12 evalInputDelta=186.56465601641963
Armijo: th(3.4598161130791205E-10)=12.310268646304866; dx=-1.8227212803225723E12 evalInputDelta=186.5646546856473
Armijo: th(2.4712972236279432E-11)=14.434011742475354; dx=-1.0272000018441623E21 evalInputDelta=184.44091158947683
Armijo: th(1.6475314824186289E-12)=133.4329651422808; dx=-1.1414054400094419E24 evalInputDelta=65.44195818967137
Armijo: th(1.029707176511643E-13)=198.87492333191918; dx=-1.82272128E24 evalInputDelta=3.299760464869905E-11
Armijo: th(6.057101038303783E-15)=198.87492333195024; dx=-1.82272128E24 evalInputDelta=1.9326762412674725E-12
MIN ALPHA (3.3650561323909904E-16): th(2.154434690031884)=0.040376148285368174
Fitness changed from 198.87492333195217 to 0.040376148285368174
Iteration 1 complete. Error: 0.040376148285368174 Total: 0.1636; Orientation: 0.0036; Line Search: 0.1205
th(0)=0.040376148285368174;dx=-6.047194801449831
New Minimum: 0.040376148285368174 > 0.04037614828536815
WOLFE (weak): th(2.154434690031884E-15)=0.04037614828536815; dx=-6.047194801449831 evalInputDelta=2.0816681711721685E-17
New Minimum: 0.04037614828536815 > 0.04037614828536813
WOLFE (weak): th(4.308869380063768E-15)=0.04037614828536813; dx=-6.047194801449831 evalInputDelta=4.163336342344337E-17
New Minimum: 0.04037614828536813 > 0.04037614828536808
WOLFE (weak): th(1.2926608140191303E-14)=0.04037614828536808; dx=-6.047194801449831 evalInputDelta=9.71445146547012E-17
New Minimum: 0.04037614828536808 > 0.04037614828536777
WOLFE (weak): th(5.1706432560765214E-14)=0.04037614828536777; dx=-6.047194801449831 evalInputDelta=4.0245584642661925E-16
New Minimum: 0.04037614828536777 > 0.040376148285366155
WOLFE (weak): th(2.5853216280382605E-13)=0.040376148285366155; dx=-6.047194801449831 evalInputDelta=2.0192181260370035E-15
New Minimum: 0.040376148285366155 > 0.04037614828535602
WOLFE (weak): th(1.5511929768229563E-12)=0.04037614828535602; dx=-6.04719480144983 evalInputDelta=1.2156942119645464E-14
New Minimum: 0.04037614828535602 > 0.04037614828528308
WOLFE (weak): th(1.0858350837760695E-11)=0.04037614828528308; dx=-6.047194801449825 evalInputDelta=8.509165594361434E-14
New Minimum: 0.04037614828528308 > 0.040376148284687476
WOLFE (weak): th(8.686680670208556E-11)=0.040376148284687476; dx=-6.04719480144978 evalInputDelta=6.806985530793952E-13
New Minimum: 0.040376148284687476 > 0.040376148279241915
WOLFE (weak): th(7.8180126031877E-10)=0.040376148279241915; dx=-6.047194801449364 evalInputDelta=6.126259222138941E-12
New Minimum: 0.040376148279241915 > 0.04037614822410559
WOLFE (weak): th(7.818012603187701E-9)=0.04037614822410559; dx=-6.047194801445157 evalInputDelta=6.126258528249551E-11
New Minimum: 0.04037614822410559 > 0.04037614761147975
WOLFE (weak): th(8.599813863506471E-8)=0.04037614761147975; dx=-6.047194801398407 evalInputDelta=6.738884242296628E-10
New Minimum: 0.04037614761147975 > 0.040376140198707465
WOLFE (weak): th(1.0319776636207765E-6)=0.040376140198707465; dx=-6.047194800832739 evalInputDelta=8.086660709116789E-9
New Minimum: 0.040376140198707465 > 0.04037604315882863
WOLFE (weak): th(1.3415709627070094E-5)=0.04037604315882863; dx=-6.047194793427639 evalInputDelta=1.051265395429768E-7
New Minimum: 0.04037604315882863 > 0.04037467652360834
WOLFE (weak): th(1.878199347789813E-4)=0.04037467652360834; dx=-6.047194689140674 evalInputDelta=1.4717617598317134E-6
New Minimum: 0.04037467652360834 > 0.04035407407351451
WOLFE (weak): th(0.0028172990216847197)=0.04035407407351451; dx=-6.047193117160092 evalInputDelta=2.2074211853663483E-5
New Minimum: 0.04035407407351451 > 0.040023529015818696
WOLFE (weak): th(0.045076784346955515)=0.040023529015818696; dx=-6.047167941883176 evalInputDelta=3.526192695494784E-4
New Minimum: 0.040023529015818696 > 0.03454015728525557
WOLFE (weak): th(0.7663053338982437)=0.03454015728525557; dx=-6.046762541377131 evalInputDelta=0.005835991000112603
New Minimum: 0.03454015728525557 > 0.0028583775118420545
WOLFE (weak): th(13.793496010168386)=0.0028583775118420545; dx=-6.0451626884359175 evalInputDelta=0.03751777077352612
New Minimum: 0.0028583775118420545 > 0.0
WOLFE (weak): th(262.07642419319933)=0.0; dx=-6.045090822743942 evalInputDelta=0.040376148285368174
WOLFE (weak): th(5241.528483863986)=0.0; dx=-6.045090822743942 evalInputDelta=0.040376148285368174
Armijo: th(110072.09816114372)=0.0; dx=-6.045090822743942 evalInputDelta=0.040376148285368174
Armijo: th(57656.813322503855)=0.0; dx=-6.045090822743942 evalInputDelta=0.040376148285368174
Armijo: th(31449.17090318392)=0.0; dx=-6.045090822743942 evalInputDelta=0.040376148285368174
Armijo: th(18345.349693523953)=0.0; dx=-6.045090822743942 evalInputDelta=0.040376148285368174
Armijo: th(11793.43908869397)=0.0; dx=-6.045090822743942 evalInputDelta=0.040376148285368174
Armijo: th(8517.483786278977)=0.0; dx=-6.045090822743942 evalInputDelta=0.040376148285368174
Armijo: th(6879.506135071482)=0.0; dx=-6.045090822743942 evalInputDelta=0.040376148285368174
WOLFE (weak): th(6060.517309467734)=0.0; dx=-6.045090822743942 evalInputDelta=0.040376148285368174
WOLFE (weak): th(6470.011722269608)=0.0; dx=-6.045090822743942 evalInputDelta=0.040376148285368174
WOLFE (weak): th(6674.758928670545)=0.0; dx=-6.045090822743942 evalInputDelta=0.040376148285368174
Armijo: th(6777.132531871013)=0.0; dx=-6.045090822743942 evalInputDelta=0.040376148285368174
Armijo: th(6725.94573027078)=0.0; dx=-6.045090822743942 evalInputDelta=0.040376148285368174
mu ~= nu (6674.758928670545): th(262.07642419319933)=0.0
Fitness changed from 0.040376148285368174 to 0.0
Iteration 2 complete. Error: 0.0 Total: 0.1604; Orientation: 0.0012; Line Search: 0.1549
th(0)=0.0;dx=-6.043728000000001
Armijo: th(14435.471494047539)=0.0; dx=-6.043728000000001 evalInputDelta=0.0
Armijo: th(7217.735747023769)=0.0; dx=-6.043728000000001 evalInputDelta=0.0
Armijo: th(2405.9119156745896)=0.0; dx=-6.043728000000001 evalInputDelta=0.0
Armijo: th(601.4779789186474)=0.0; dx=-6.043728000000001 evalInputDelta=0.0
Armijo: th(120.29559578372948)=0.0; dx=-6.043728000000001 evalInputDelta=0.0
Armijo: th(20.049265963954912)=0.0; dx=-6.043728000000001 evalInputDelta=0.0
Armijo: th(2.864180851993559)=0.0; dx=-6.043728000000001 evalInputDelta=0.0
Armijo: th(0.3580226064991949)=0.0; dx=-6.043728000000001 evalInputDelta=0.0
Armijo: th(0.03978028961102165)=0.0; dx=-6.043728000000001 evalInputDelta=0.0
Armijo: th(0.0039780289611021655)=0.0; dx=-6.043728000000001 evalInputDelta=0.0
Armijo: th(3.616389964638332E-4)=0.0; dx=-6.043728000000001 evalInputDelta=0.0
Armijo: th(3.013658303865277E-5)=0.0; dx=-6.043728000000001 evalInputDelta=0.0
Armijo: th(2.318198695280982E-6)=0.0; dx=-6.043728000000001 evalInputDelta=0.0
Armijo: th(1.6558562109149874E-7)=0.0; dx=-6.043728000000001 evalInputDelta=0.0
Armijo: th(1.1039041406099916E-8)=0.0; dx=-6.043728000000001 evalInputDelta=0.0
Armijo: th(6.899400878812448E-10)=0.0; dx=-6.043728000000001 evalInputDelta=0.0
Armijo: th(4.0584711051837925E-11)=0.0; dx=-6.043728000000001 evalInputDelta=0.0
Armijo: th(2.2547061695465513E-12)=0.0; dx=-6.043728000000001 evalInputDelta=0.0
Armijo: th(1.1866874576560797E-13)=0.0; dx=-6.043728000000001 evalInputDelta=0.0
Armijo: th(5.9334372882803985E-15)=0.0; dx=-6.043728000000001 evalInputDelta=0.0
MIN ALPHA (2.825446327752571E-16): th(0.0)=0.0
Fitness changed from 0.0 to 0.0
Static Iteration Total: 0.2998; Orientation: 0.0007; Line Search: 0.2977
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 0.624s (< 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 0.30 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: 1249280180997
Reset training subject: 1249281725442
Constructing line search parameters: GD
F(0.0) = LineSearchPoint{point=PointSample{avg=198.87492333195217}, derivative=-1.82272128E24}
New Minimum: 198.87492333195217 > 12.676147690451124
F(1.0E-10) = LineSearchPoint{point=PointSample{avg=12.676147690451124}, derivative=-6.272000182538238E19}, evalInputDelta = -186.19877564150104
New Minimum: 12.676147690451124 > 12.310268532831103
F(7.000000000000001E-10) = LineSearchPoint{point=PointSample{avg=12.310268532831103}, derivative=-1.8227212803225723E12}, evalInputDelta = -186.56465479912106
New Minimum: 12.310268532831103 > 12.310267186602672
F(4.900000000000001E-9) = LineSearchPoint{point=PointSample{avg=12.310267186602672}, derivative=-1.8227212803225723E12}, evalInputDelta = -186.5646561453495
New Minimum: 12.310267186602672 > 12.31025776302935
F(3.430000000000001E-8) = LineSearchPoint{point=PointSample{avg=12.31025776302935}, derivative=-1.8227212803225703E12}, evalInputDelta = -186.56466556892283
New Minimum: 12.31025776302935 > 12.31019179927572
F(2.4010000000000004E-7) = LineSearchPoint{point=PointSample{avg=12.31019179927572}, derivative=-1.82272128032256E12}, evalInputDelta = -186.56473153267646
New Minimum: 12.31019179927572 > 12.309730114706745
F(1.6807000000000003E-6) = LineSearchPoint{point=PointSample{avg=12.309730114706745}, derivative=-1.8227212803224849E12}, evalInputDelta = -186.56519321724542
New Minimum: 12.309730114706745 > 12.306501341175316
F(1.1764900000000001E-5) = LineSearchPoint{point=PointSample{avg=12.306501341175316}, derivative=-1.8227212803219617E12}, evalInputDelta = -186.56842199077687
New Minimum: 12.306501341175316 > 12.284046085827018
F(8.235430000000001E-5) = LineSearchPoint{point=PointSample{avg=12.284046085827018}, derivative=-1.8227212803183616E12}, evalInputDelta = -186.59087724612516
New Minimum: 12.284046085827018 > 12.133479520045304
F(5.764801000000001E-4) = LineSearchPoint{point=PointSample{avg=12.133479520045304}, derivative=-1.8227212802958855E12}, evalInputDelta = -186.74144381190686
New Minimum: 12.133479520045304 > 11.293934437157725
F(0.004035360700000001) = LineSearchPoint{point=PointSample{avg=11.293934437157725}, derivative=-1.8227212802072056E12}, evalInputDelta = -187.58098889479444
New Minimum: 11.293934437157725 > 8.37186600484631
F(0.028247524900000005) = LineSearchPoint{point=PointSample{avg=8.37186600484631}, derivative=-1.822721280082252E12}, evalInputDelta = -190.50305732710586
New Minimum: 8.37186600484631 > 2.792915176482467
F(0.19773267430000002) = LineSearchPoint{point=PointSample{avg=2.792915176482467}, derivative=-1.8227212800244333E12}, evalInputDelta = -196.0820081554697
New Minimum: 2.792915176482467 > 0.08656979239772204
F(1.3841287201) = LineSearchPoint{point=PointSample{avg=0.08656979239772204}, derivative=-1.8227212800199978E12}, evalInputDelta = -198.78835353955446
New Minimum: 0.08656979239772204 > 0.007319773895792724
F(9.688901040700001) = LineSearchPoint{point=PointSample{avg=0.007319773895792724}, derivative=-1.8227212800199756E12}, evalInputDelta = -198.86760355805637
New Minimum: 0.007319773895792724 > 0.0
F(67.8223072849) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-1.822721280019975E12}, evalInputDelta = -198.87492333195217
F(474.7561509943) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-1.822721280019975E12}, evalInputDelta = -198.87492333195217
F(3323.2930569601003) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-1.822721280019975E12}, evalInputDelta = -198.87492333195217
F(23263.0513987207) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-1.822721280019975E12}, evalInputDelta = -198.87492333195217
F(162841.3597910449) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-1.822721280019975E12}, evalInputDelta = -198.87492333195217
F(1139889.5185373144) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-1.822721280019975E12}, evalInputDelta = -198.87492333195217
F(7979226.6297612) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-1.822721280019975E12}, evalInputDelta = -198.87492333195217
F(5.58545864083284E7) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-1.822721280019975E12}, evalInputDelta = -198.87492333195217
F(3.909821048582988E8) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-1.822721280019975E12}, evalInputDelta = -198.87492333195217
F(2.7368747340080914E9) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-1.822721280019975E12}, evalInputDelta = -198.87492333195217
F(1.915812313805664E10) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-1.822721280019975E12}, evalInputDelta = -198.87492333195217
0.0 <= 198.87492333195217
F(1.0E10) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-1.822721280019975E12}, evalInputDelta = -198.87492333195217
Right bracket at 1.0E10
Converged to right
Fitness changed from 198.87492333195217 to 0.0
Iteration 1 complete. Error: 0.0 Total: 0.2057; Orientation: 0.0010; Line Search: 0.1979
F(0.0) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-6.043728000000001}
F(1.0E10) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-6.043728000000001}, evalInputDelta = 0.0
0.0 <= 0.0
F(5.0E9) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-6.043728000000001}, evalInputDelta = 0.0
Right bracket at 5.0E9
F(2.5E9) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-6.043728000000001}, evalInputDelta = 0.0
Right bracket at 2.5E9
F(1.25E9) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-6.043728000000001}, evalInputDelta = 0.0
Right bracket at 1.25E9
F(6.25E8) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-6.043728000000001}, evalInputDelta = 0.0
Right bracket at 6.25E8
F(3.125E8) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-6.043728000000001}, evalInputDelta = 0.0
Right bracket at 3.125E8
F(1.5625E8) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-6.043728000000001}, evalInputDelta = 0.0
Right bracket at 1.5625E8
F(7.8125E7) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-6.043728000000001}, evalInputDelta = 0.0
Right bracket at 7.8125E7
F(3.90625E7) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-6.043728000000001}, evalInputDelta = 0.0
Right bracket at 3.90625E7
F(1.953125E7) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-6.043728000000001}, evalInputDelta = 0.0
Right bracket at 1.953125E7
F(9765625.0) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-6.043728000000001}, evalInputDelta = 0.0
Right bracket at 9765625.0
F(4882812.5) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-6.043728000000001}, evalInputDelta = 0.0
Right bracket at 4882812.5
F(2441406.25) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-6.043728000000001}, evalInputDelta = 0.0
Loops = 12
Fitness changed from 0.0 to 0.0
Static Iteration Total: 0.0951; Orientation: 0.0010; Line Search: 0.0921
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 0.302s (< 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 6.43 seconds (0.060 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: 1249587139657
Reset training subject: 1249588953090
Adding measurement 3abb88f2 to history. Total: 0
LBFGS Accumulation History: 1 points
Constructing line search parameters: GD
Non-optimal measurement 198.87492333195217 < 198.87492333195217. Total: 1
th(0)=198.87492333195217;dx=-1.82272128E24
Adding measurement 76ba2d72 to history. Total: 1
New Minimum: 198.87492333195217 > 0.040376148285368174
Armijo: th(2.154434690031884)=0.040376148285368174; dx=-1.8227212800199805E12 evalInputDelta=198.8345471836668
Non-optimal measurement 0.13565768176441656 < 0.040376148285368174. Total: 2
Armijo: th(1.077217345015942)=0.13565768176441656; dx=-1.822721280020022E12 evalInputDelta=198.73926565018775
Non-optimal measurement 1.5084087331159235 < 0.040376148285368174. Total: 2
Armijo: th(0.3590724483386473)=1.5084087331159235; dx=-1.822721280021404E12 evalInputDelta=197.36651459883626
Non-optimal measurement 5.192915663551141 < 0.040376148285368174. Total: 2
Armijo: th(0.08976811208466183)=5.192915663551141; dx=-1.8227212800380686E12 evalInputDelta=193.68200766840104
Non-optimal measurement 9.313358984575963 < 0.040376148285368174. Total: 2
Armijo: th(0.017953622416932366)=9.313358984575963; dx=-1.8227212801073335E12 evalInputDelta=189.56156434737622
Non-optimal measurement 11.517506629001524 < 0.040376148285368174. Total: 2
Armijo: th(0.002992270402822061)=11.517506629001524; dx=-1.8227212802262598E12 evalInputDelta=187.35741670295064
Non-optimal measurement 12.177732642077945 < 0.040376148285368174. Total: 2
Armijo: th(4.2746720040315154E-4)=12.177732642077945; dx=-1.8227212803022075E12 evalInputDelta=186.69719068987422
Non-optimal measurement 12.293215439192874 < 0.040376148285368174. Total: 2
Armijo: th(5.343340005039394E-5)=12.293215439192874; dx=-1.8227212803198232E12 evalInputDelta=186.5817078927593
Non-optimal measurement 12.30836666855716 < 0.040376148285368174. Total: 2
Armijo: th(5.9370444500437714E-6)=12.30836666855716; dx=-1.8227212803222637E12 evalInputDelta=186.566556663395
Non-optimal measurement 12.310078465858734 < 0.040376148285368174. Total: 2
Armijo: th(5.937044450043771E-7)=12.310078465858734; dx=-1.8227212803225415E12 evalInputDelta=186.56484486609344
Non-optimal measurement 12.310251457231484 < 0.040376148285368174. Total: 2
Armijo: th(5.397313136403428E-8)=12.310251457231484; dx=-1.8227212803225696E12 evalInputDelta=186.5646718747207
Non-optimal measurement 12.310267315532547 < 0.040376148285368174. Total: 2
Armijo: th(4.4977609470028565E-9)=12.310267315532547; dx=-1.8227212803225723E12 evalInputDelta=186.56465601641963
Non-optimal measurement 12.310268646304866 < 0.040376148285368174. Total: 2
Armijo: th(3.4598161130791205E-10)=12.310268646304866; dx=-1.8227212803225723E12 evalInputDelta=186.5646546856473
Non-optimal measurement 14.434011742475354 < 0.040376148285368174. Total: 2
Armijo: th(2.4712972236279432E-11)=14.434011742475354; dx=-1.0272000018441623E21 evalInputDelta=184.44091158947683
Non-optimal measurement 133.4329651422808 < 0.040376148285368174. Total: 2
Armijo: th(1.6475314824186289E-12)=133.4329651422808; dx=-1.1414054400094419E24 evalInputDelta=65.44195818967137
Non-optimal measurement 198.87492333191918 < 0.040376148285368174. Total: 2
Armijo: th(1.029707176511643E-13)=198.87492333191918; dx=-1.82272128E24 evalInputDelta=3.299760464869905E-11
Non-optimal measurement 198.87492333195024 < 0.040376148285368174. Total: 2
Armijo: th(6.057101038303783E-15)=198.87492333195024; dx=-1.82272128E24 evalInputDelta=1.9326762412674725E-12
Non-optimal measurement 0.040376148285368174 < 0.040376148285368174. Total: 2
MIN ALPHA (3.3650561323909904E-16): th(2.154434690031884)=0.040376148285368174
Fitness changed from 198.87492333195217 to 0.040376148285368174
Iteration 1 complete. Error: 0.040376148285368174 Total: 0.1446; Orientation: 0.0037; Line Search: 0.1355
Non-optimal measurement 0.040376148285368174 < 0.040376148285368174. Total: 2
LBFGS Accumulation History: 2 points
Non-optimal measurement 0.040376148285368174 < 0.040376148285368174. Total: 2
th(0)=0.040376148285368174;dx=-6.047194801449831
Adding measurement 11500880 to history. Total: 2
New Minimum: 0.040376148285368174 > 0.04037614828536815
WOLFE (weak): th(2.154434690031884E-15)=0.04037614828536815; dx=-6.047194801449831 evalInputDelta=2.0816681711721685E-17
Adding measurement 19298289 to history. Total: 3
New Minimum: 0.04037614828536815 > 0.04037614828536813
WOLFE (weak): th(4.308869380063768E-15)=0.04037614828536813; dx=-6.047194801449831 evalInputDelta=4.163336342344337E-17
Adding measurement 65f5e102 to history. Total: 4
New Minimum: 0.04037614828536813 > 0.04037614828536808
WOLFE (weak): th(1.2926608140191303E-14)=0.04037614828536808; dx=-6.047194801449831 evalInputDelta=9.71445146547012E-17
Adding measurement 479bd527 to history. Total: 5
New Minimum: 0.04037614828536808 > 0.04037614828536777
WOLFE (weak): th(5.1706432560765214E-14)=0.04037614828536777; dx=-6.047194801449831 evalInputDelta=4.0245584642661925E-16
Adding measurement 69ce309e to history. Total: 6
New Minimum: 0.04037614828536777 > 0.040376148285366155
WOLFE (weak): th(2.5853216280382605E-13)=0.040376148285366155; dx=-6.047194801449831 evalInputDelta=2.0192181260370035E-15
Adding measurement 5f5767b4 to history. Total: 7
New Minimum: 0.040376148285366155 > 0.04037614828535602
WOLFE (weak): th(1.5511929768229563E-12)=0.04037614828535602; dx=-6.04719480144983 evalInputDelta=1.2156942119645464E-14
Adding measurement b5e9384 to history. Total: 8
New Minimum: 0.04037614828535602 > 0.04037614828528308
WOLFE (weak): th(1.0858350837760695E-11)=0.04037614828528308; dx=-6.047194801449825 evalInputDelta=8.509165594361434E-14
Adding measurement 7e45102a to history. Total: 9
New Minimum: 0.04037614828528308 > 0.040376148284687476
WOLFE (weak): th(8.686680670208556E-11)=0.040376148284687476; dx=-6.04719480144978 evalInputDelta=6.806985530793952E-13
Adding measurement 2ee8877a to history. Total: 10
New Minimum: 0.040376148284687476 > 0.040376148279241915
WOLFE (weak): th(7.8180126031877E-10)=0.040376148279241915; dx=-6.047194801449364 evalInputDelta=6.126259222138941E-12
Adding measurement 492a5502 to history. Total: 11
New Minimum: 0.040376148279241915 > 0.04037614822410559
WOLFE (weak): th(7.818012603187701E-9)=0.04037614822410559; dx=-6.047194801445157 evalInputDelta=6.126258528249551E-11
Adding measurement 3ffe108 to history. Total: 12
New Minimum: 0.04037614822410559 > 0.04037614761147975
WOLFE (weak): th(8.599813863506471E-8)=0.04037614761147975; dx=-6.047194801398407 evalInputDelta=6.738884242296628E-10
Adding measurement 3b1bf09b to history. Total: 13
New Minimum: 0.04037614761147975 > 0.040376140198707465
WOLFE (weak): th(1.0319776636207765E-6)=0.040376140198707465; dx=-6.047194800832739 evalInputDelta=8.086660709116789E-9
Adding measurement 5719dfa0 to history. Total: 14
New Minimum: 0.040376140198707465 > 0.04037604315882863
WOLFE (weak): th(1.3415709627070094E-5)=0.04037604315882863; dx=-6.047194793427639 evalInputDelta=1.051265395429768E-7
Adding measurement 41f6ab74 to history. Total: 15
New Minimum: 0.04037604315882863 > 0.04037467652360834
WOLFE (weak): th(1.878199347789813E-4)=0.04037467652360834; dx=-6.047194689140674 evalInputDelta=1.4717617598317134E-6
Adding measurement 2e154248 to history. Total: 16
New Minimum: 0.04037467652360834 > 0.04035407407351451
WOLFE (weak): th(0.0028172990216847197)=0.04035407407351451; dx=-6.047193117160092 evalInputDelta=2.2074211853663483E-5
Adding measurement 39ab6d6b to history. Total: 17
New Minimum: 0.04035407407351451 > 0.040023529015818696
WOLFE (weak): th(0.045076784346955515)=0.040023529015818696; dx=-6.047167941883176 evalInputDelta=3.526192695494784E-4
Adding measurement 6b4c5d85 to history. Total: 18
New Minimum: 0.040023529015818696 > 0.03454015728525557
WOLFE (weak): th(0.7663053338982437)=0.03454015728525557; dx=-6.046762541377131 evalInputDelta=0.005835991000112603
Adding measurement 2373dda0 to history. Total: 19
New Minimum: 0.03454015728525557 > 0.0028583775118420545
WOLFE (weak): th(13.793496010168386)=0.0028583775118420545; dx=-6.0451626884359175 evalInputDelta=0.03751777077352612
Adding measurement 7eb150e3 to his

...skipping 9866 bytes...

-b366-245ead18fc96 = 1.000/1.000e+00, e55873f5-2f0c-4639-acd5-8dc2b2522f86 = 1.000/1.000e+00, 570e0df9-534e-459b-8725-94dac0baf354 = 1.000/1.000e+00, af162d35-4869-4ecb-9f30-997728b4a46e = 1.000/1.000e+00, bc4a741b-71ed-4a6a-b5e4-06c630ddf5ed = 1.000/1.000e+00]
Orientation rejected. Popping history element from 0.0, 0.0028583775118420545, 0.03454015728525557, 0.040023529015818696, 0.04035407407351451, 0.04037467652360834, 0.04037604315882863, 0.040376140198707465, 0.04037614761147975, 0.04037614822410559, 0.040376148279241915
Rejected: LBFGS Orientation magnitude: 3.965e+04, gradient 2.458e+00, dot -0.989; [e55873f5-2f0c-4639-acd5-8dc2b2522f86 = 1.000/1.000e+00, af162d35-4869-4ecb-9f30-997728b4a46e = 1.000/1.000e+00, bc4a741b-71ed-4a6a-b5e4-06c630ddf5ed = 1.000/1.000e+00, 4d59b0cc-3207-419b-b366-245ead18fc96 = 1.000/1.000e+00, 570e0df9-534e-459b-8725-94dac0baf354 = 1.000/1.000e+00]
Orientation rejected. Popping history element from 0.0, 0.0028583775118420545, 0.03454015728525557, 0.040023529015818696, 0.04035407407351451, 0.04037467652360834, 0.04037604315882863, 0.040376140198707465, 0.04037614761147975, 0.04037614822410559
Rejected: LBFGS Orientation magnitude: 3.965e+04, gradient 2.458e+00, dot -0.989; [570e0df9-534e-459b-8725-94dac0baf354 = 1.000/1.000e+00, bc4a741b-71ed-4a6a-b5e4-06c630ddf5ed = 1.000/1.000e+00, af162d35-4869-4ecb-9f30-997728b4a46e = 1.000/1.000e+00, e55873f5-2f0c-4639-acd5-8dc2b2522f86 = 1.000/1.000e+00, 4d59b0cc-3207-419b-b366-245ead18fc96 = 1.000/1.000e+00]
Orientation rejected. Popping history element from 0.0, 0.0028583775118420545, 0.03454015728525557, 0.040023529015818696, 0.04035407407351451, 0.04037467652360834, 0.04037604315882863, 0.040376140198707465, 0.04037614761147975
Rejected: LBFGS Orientation magnitude: 3.965e+04, gradient 2.458e+00, dot -0.989; [4d59b0cc-3207-419b-b366-245ead18fc96 = 1.000/1.000e+00, e55873f5-2f0c-4639-acd5-8dc2b2522f86 = 1.000/1.000e+00, 570e0df9-534e-459b-8725-94dac0baf354 = 1.000/1.000e+00, bc4a741b-71ed-4a6a-b5e4-06c630ddf5ed = 1.000/1.000e+00, af162d35-4869-4ecb-9f30-997728b4a46e = 1.000/1.000e+00]
Orientation rejected. Popping history element from 0.0, 0.0028583775118420545, 0.03454015728525557, 0.040023529015818696, 0.04035407407351451, 0.04037467652360834, 0.04037604315882863, 0.040376140198707465
Rejected: LBFGS Orientation magnitude: 5.119e+04, gradient 2.458e+00, dot -0.969; [570e0df9-534e-459b-8725-94dac0baf354 = 1.000/1.000e+00, 4d59b0cc-3207-419b-b366-245ead18fc96 = 1.000/1.000e+00, af162d35-4869-4ecb-9f30-997728b4a46e = 1.000/1.000e+00, bc4a741b-71ed-4a6a-b5e4-06c630ddf5ed = 1.000/1.000e+00, e55873f5-2f0c-4639-acd5-8dc2b2522f86 = 1.000/1.000e+00]
Orientation rejected. Popping history element from 0.0, 0.0028583775118420545, 0.03454015728525557, 0.040023529015818696, 0.04035407407351451, 0.04037467652360834, 0.04037604315882863
Rejected: LBFGS Orientation magnitude: 4.976e+04, gradient 2.458e+00, dot -1.000; [4d59b0cc-3207-419b-b366-245ead18fc96 = 1.000/1.000e+00, af162d35-4869-4ecb-9f30-997728b4a46e = 1.000/1.000e+00, e55873f5-2f0c-4639-acd5-8dc2b2522f86 = 1.000/1.000e+00, bc4a741b-71ed-4a6a-b5e4-06c630ddf5ed = 1.000/1.000e+00, 570e0df9-534e-459b-8725-94dac0baf354 = 1.000/1.000e+00]
Orientation rejected. Popping history element from 0.0, 0.0028583775118420545, 0.03454015728525557, 0.040023529015818696, 0.04035407407351451, 0.04037467652360834
Rejected: LBFGS Orientation magnitude: 4.989e+04, gradient 2.458e+00, dot -1.000; [bc4a741b-71ed-4a6a-b5e4-06c630ddf5ed = 1.000/1.000e+00, af162d35-4869-4ecb-9f30-997728b4a46e = 1.000/1.000e+00, e55873f5-2f0c-4639-acd5-8dc2b2522f86 = 1.000/1.000e+00, 570e0df9-534e-459b-8725-94dac0baf354 = 1.000/1.000e+00, 4d59b0cc-3207-419b-b366-245ead18fc96 = 1.000/1.000e+00]
Orientation rejected. Popping history element from 0.0, 0.0028583775118420545, 0.03454015728525557, 0.040023529015818696, 0.04035407407351451
Rejected: LBFGS Orientation magnitude: 5.288e+04, gradient 2.458e+00, dot -1.000; [e55873f5-2f0c-4639-acd5-8dc2b2522f86 = 1.000/1.000e+00, bc4a741b-71ed-4a6a-b5e4-06c630ddf5ed = 1.000/1.000e+00, af162d35-4869-4ecb-9f30-997728b4a46e = 1.000/1.000e+00, 4d59b0cc-3207-419b-b366-245ead18fc96 = 1.000/1.000e+00, 570e0df9-534e-459b-8725-94dac0baf354 = 1.000/1.000e+00]
Orientation rejected. Popping history element from 0.0, 0.0028583775118420545, 0.03454015728525557, 0.040023529015818696
LBFGS Accumulation History: 3 points
Removed measurement 7eb150e3 to history. Total: 20
Removed measurement 2373dda0 to history. Total: 19
Removed measurement 6b4c5d85 to history. Total: 18
Removed measurement 39ab6d6b to history. Total: 17
Removed measurement 2e154248 to history. Total: 16
Removed measurement 41f6ab74 to history. Total: 15
Removed measurement 5719dfa0 to history. Total: 14
Removed measurement 3b1bf09b to history. Total: 13
Removed measurement 3ffe108 to history. Total: 12
Removed measurement 492a5502 to history. Total: 11
Removed measurement 2ee8877a to history. Total: 10
Removed measurement 7e45102a to history. Total: 9
Removed measurement b5e9384 to history. Total: 8
Removed measurement 5f5767b4 to history. Total: 7
Removed measurement 69ce309e to history. Total: 6
Removed measurement 479bd527 to history. Total: 5
Removed measurement 65f5e102 to history. Total: 4
Removed measurement 19298289 to history. Total: 3
Adding measurement 10f92e67 to history. Total: 3
th(0)=0.0;dx=-6.043728000000001
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(14435.471494047539)=0.0; dx=-6.043728000000001 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(7217.735747023769)=0.0; dx=-6.043728000000001 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(2405.9119156745896)=0.0; dx=-6.043728000000001 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(601.4779789186474)=0.0; dx=-6.043728000000001 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(120.29559578372948)=0.0; dx=-6.043728000000001 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(20.049265963954912)=0.0; dx=-6.043728000000001 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(2.864180851993559)=0.0; dx=-6.043728000000001 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(0.3580226064991949)=0.0; dx=-6.043728000000001 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(0.03978028961102165)=0.0; dx=-6.043728000000001 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(0.0039780289611021655)=0.0; dx=-6.043728000000001 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(3.616389964638332E-4)=0.0; dx=-6.043728000000001 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(3.013658303865277E-5)=0.0; dx=-6.043728000000001 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(2.318198695280982E-6)=0.0; dx=-6.043728000000001 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(1.6558562109149874E-7)=0.0; dx=-6.043728000000001 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(1.1039041406099916E-8)=0.0; dx=-6.043728000000001 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(6.899400878812448E-10)=0.0; dx=-6.043728000000001 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(4.0584711051837925E-11)=0.0; dx=-6.043728000000001 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(2.2547061695465513E-12)=0.0; dx=-6.043728000000001 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(1.1866874576560797E-13)=0.0; dx=-6.043728000000001 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(5.9334372882803985E-15)=0.0; dx=-6.043728000000001 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
MIN ALPHA (2.825446327752571E-16): th(0.0)=0.0
Fitness changed from 0.0 to 0.0
Static Iteration Total: 5.9319; Orientation: 5.8568; Line Search: 0.0732
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 6.433s (< 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, -2.3938751132823235], [2.0, -0.3938751132823235]; valueStats=DoubleSummaryStatistics{count=2, sum=0.080752, min=0.040376, average=0.040376, max=0.040376}
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, -2.3938751132823235], [0.356, -0.3938751132823235]; valueStats=DoubleSummaryStatistics{count=2, sum=0.080752, min=0.040376, average=0.040376, max=0.040376}
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": "8.078",
      "gc_time": "0.306"
    },
    "created_on": 1586735836443,
    "file_name": "trainingTest",
    "report": {
      "simpleName": "Basic",
      "canonicalName": "com.simiacryptus.mindseye.layers.java.ReshapeLayerTest.Basic",
      "link": "https://github.com/SimiaCryptus/mindseye-java/tree/93db34cedee48c0202777a2b25deddf1dfaf5731/src/test/java/com/simiacryptus/mindseye/layers/java/ReshapeLayerTest.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/ReshapeLayer/Basic/trainingTest/202004125716",
    "id": "c9036981-8966-4016-8ad1-f49565c5811a",
    "report_type": "Components",
    "display_name": "Comparative Training",
    "target": {
      "simpleName": "ReshapeLayer",
      "canonicalName": "com.simiacryptus.mindseye.layers.java.ReshapeLayer",
      "link": "https://github.com/SimiaCryptus/mindseye-java/tree/93db34cedee48c0202777a2b25deddf1dfaf5731/src/main/java/com/simiacryptus/mindseye/layers/java/ReshapeLayer.java",
      "javaDoc": ""
    }
  }