SOTAVerified

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

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1201–1250 of 1387 papers

TitleStatusHype
Biased Importance Sampling for Deep Neural Network TrainingCode0
Limited-Memory Matrix Adaptation for Large Scale Black-box OptimizationCode0
Comments on the proof of adaptive submodular function minimization—0
Accelerating Stochastic Gradient Descent For Least Squares Regression—0
Stochastic Optimization from Distributed, Streaming Data in Rate-limited Networks—0
Bandit Structured Prediction for Neural Sequence-to-Sequence LearningCode0
Performance Limits of Stochastic Sub-Gradient Learning, Part II: Multi-Agent Case—0
Importance Sampled Stochastic Optimization for Variational Inference—0
Larger is Better: The Effect of Learning Rates Enjoyed by Stochastic Optimization with Progressive Variance Reduction—0
Probabilistic Line Searches for Stochastic OptimizationCode0
Stochastic Primal Dual Coordinate Method with Non-Uniform Sampling Based on Optimality Violations—0
Guaranteed Sufficient Decrease for Variance Reduced Stochastic Gradient Descent—0
Incorporating statistical model error into the calculation of acceptability prices of contingent claims—0
Langevin Dynamics with Continuous Tempering for Training Deep Neural Networks—0
Task-based End-to-end Model Learning in Stochastic OptimizationCode0
Learning to Optimize Neural Nets—0
Dual Iterative Hard Thresholding: From Non-convex Sparse Minimization to Non-smooth Concave Maximization—0
Fast Rates for Bandit Optimization with Upper-Confidence Frank-Wolfe—0
Memory and Communication Efficient Distributed Stochastic Optimization with Minibatch-Prox—0
Stochastic Canonical Correlation Analysis—0
Revisiting Distributed Synchronous SGD—0
Natasha: Faster Non-Convex Stochastic Optimization Via Strongly Non-Convex Parameter—0
Communication-Efficient Algorithms for Decentralized and Stochastic Optimization—0
Maximum Entropy Flow Networks—0
Stochastic Multidimensional Scaling—0
Asymptotic Optimality in Stochastic Optimization—0
Coupling Adaptive Batch Sizes with Learning RatesCode0
An empirical analysis of the optimization of deep network loss surfaces—0
Without-Replacement Sampling for Stochastic Gradient Methods—0
One-vs-Each Approximation to Softmax for Scalable Estimation of Probabilities—0
Scalable Bayesian Learning of Recurrent Neural Networks for Language Modeling—0
Optimal Learning for Stochastic Optimization with Nonlinear Parametric Belief Models—0
Optimizing connection weights in neural networks using the whale optimization algorithm—0
Scalable Adaptive Stochastic Optimization Using Random Projections—0
Scalable Approximations for Generalized Linear Problems—0
Faster variational inducing input Gaussian process classification—0
A Generalized Stochastic Variational Bayesian Hyperparameter Learning Framework for Sparse Spectrum Gaussian Process Regression—0
The Asset Liability Management problem of a nuclear operator : a numerical stochastic optimization approach—0
Greedy Step Averaging: A parameter-free stochastic optimization methodCode0
Learning from Untrusted Data—0
Eve: A Gradient Based Optimization Method with Locally and Globally Adaptive Learning RatesCode0
Learning Deep Embeddings with Histogram LossCode0
Asynchronous Stochastic Block Coordinate Descent with Variance Reduction—0
Reparameterization Gradients through Acceptance-Rejection Sampling AlgorithmsCode0
Statistics of Robust Optimization: A Generalized Empirical Likelihood Approach—0
Variance-based regularization with convex objectivesCode0
Boost K-Means—0
Stochastic Optimization with Variance Reduction for Infinite Datasets with Finite-Sum StructureCode0
Exact and Inexact Subsampled Newton Methods for Optimization—0
Sooner than Expected: Hitting the Wall of Complexity in Evolution—0
Show:102550
← PrevPage 25 of 28Next →
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

#ModelMetricClaimedVerifiedStatus
1AvaGradAccuracy81.24—Unverified
2AdaShiftAccuracy81.12—Unverified
3Adam (eps-adjusted)Accuracy81.04—Unverified
4SGDAccuracy80.95—Unverified
5AdamWAccuracy79.87—Unverified
6AdaBoundAccuracy77.24—Unverified
#ModelMetricClaimedVerifiedStatus
1Adam (eps-adjusted)Accuracy96.36—Unverified
2AvaGradAccuracy96.2—Unverified
3SGDAccuracy96.14—Unverified
4AdaShiftAccuracy95.92—Unverified
5AdamWAccuracy95.89—Unverified
6AdaBoundAccuracy94.6—Unverified
#ModelMetricClaimedVerifiedStatus
1SGD - cosine LR scheduleAccuracy95.55—Unverified
2LookaheadAccuracy95.27—Unverified
3SGDAccuracy95.23—Unverified
4ADAMAccuracy94.84—Unverified
#ModelMetricClaimedVerifiedStatus
1AvaGradTop 1 Accuracy76.51—Unverified
2SGDTop 1 Accuracy75.99—Unverified
3AdamWTop 1 Accuracy72.9—Unverified
4AdaBoundTop 1 Accuracy72.01—Unverified
#ModelMetricClaimedVerifiedStatus
1AdaBoundBit per Character (BPC)2.86—Unverified
2AdaShiftBit per Character (BPC)1.27—Unverified
3AdamWBit per Character (BPC)1.23—Unverified
4AvaGradBit per Character (BPC)1.18—Unverified
#ModelMetricClaimedVerifiedStatus
1Resnet18Accuracy (max)86.85—Unverified
2Resnet34Accuracy (max)86.14—Unverified
#ModelMetricClaimedVerifiedStatus
1Resnet18Accuracy (max)58.48—Unverified
2Resnet34Accuracy (max)54.5—Unverified
#ModelMetricClaimedVerifiedStatus
1SGDTop 5 Accuracy92.15—Unverified
2LookaheadTop 1 Accuracy75.13—Unverified
#ModelMetricClaimedVerifiedStatus
1LookaheadTop 1 Accuracy75.49—Unverified
2SGDTop 1 Accuracy75.15—Unverified
#ModelMetricClaimedVerifiedStatus
1BertAccuracy (max)93.99—Unverified
#ModelMetricClaimedVerifiedStatus
1BertAccuracy (max)86.34—Unverified
#ModelMetricClaimedVerifiedStatus
1MLPNLL0.05—Unverified