Stochastic Optimization
Stochastic Optimization is the task of optimizing certain objective functional by generating and using stochastic random variables. Usually the Stochastic Optimization is an iterative process of generating random variables that progressively finds out the minima or the maxima of the objective functional. Stochastic Optimization is usually applied in the non-convex functional spaces where the usual deterministic optimization such as linear or quadratic programming or their variants cannot be used.
Source: ASOC: An Adaptive Parameter-free Stochastic Optimization Techinique for Continuous Variables
Papers
Showing 126–150 of 1387 papers
All datasetsCIFAR-100 WRN-28-10 - 200 EpochsCIFAR-10 WRN-28-10 - 200 EpochsCIFAR-10 ResNet-18 - 200 EpochsImageNet ResNet-50 - 90 EpochsPenn Treebank (Character Level) 3x1000 LSTM - 500 EpochsCIFAR-10CIFAR-100ImageNet ResNet-50 - 50 EpochsImageNet ResNet-50 - 60 EpochsAG NewsCoLAMNIST
Benchmark Results
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | SGD - cosine LR schedule | Accuracy | 95.55 | — | Unverified |
| 2 | Lookahead | Accuracy | 95.27 | — | Unverified |
| 3 | SGD | Accuracy | 95.23 | — | Unverified |
| 4 | ADAM | Accuracy | 94.84 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | Bert | Accuracy (max) | 93.99 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | Bert | Accuracy (max) | 86.34 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | MLP | NLL | 0.05 | — | Unverified |