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 401–450 of 1387 papers

TitleStatusHype
Risk-Adaptive Approaches to Stochastic Optimization: A Survey—0
Stochastic Steffensen method—0
End-to-End Stochastic Optimization with Energy-Based ModelCode1
Sensitivity Analyses of Resilience-oriented Risk-averse Active Distribution Systems Planning—0
Bandit Algorithms for Prophet Inequality and Pandora's Box—0
SketchySGD: Reliable Stochastic Optimization via Randomized Curvature EstimatesCode0
Scalable PAC-Bayesian Meta-Learning via the PAC-Optimal Hyper-Posterior: From Theory to Practice—0
RFFNet: Large-Scale Interpretable Kernel Methods via Random Fourier FeaturesCode0
Toward Neural Network Simulation of Variational Quantum Algorithms—0
Augmentation Invariant Manifold Learning—0
Optimal Complexity in Non-Convex Decentralized Learning over Time-Varying Networks—0
Local Model Reconstruction Attacks in Federated Learning and their Uses—0
Solving the Schrodinger equation with genetic algorithms: a practical approach—0
Federated Learning Using Variance Reduced Stochastic Gradient for Probabilistically Activated Agents—0
Langevin dynamics based algorithm e-THO POULA for stochastic optimization problems with discontinuous stochastic gradientCode0
Stochastic Mirror Descent for Large-Scale Sparse Recovery—0
Decentralized Stochastic Bilevel Optimization with Improved per-Iteration Complexity—0
On-Demand Sampling: Learning Optimally from Multiple DistributionsCode0
FLECS-CGD: A Federated Learning Second-Order Framework via Compression and Sketching with Compressed Gradient Differences—0
Stochastic Differentially Private and Fair LearningCode0
Hierarchical Policy Blending as Inference for Reactive Robot Control—0
Joint control variate for faster black-box variational inferenceCode0
A General Stochastic Optimization Framework for Convergence Bidding—0
Zero-Order One-Point Estimate with Distributed Stochastic Gradient-Tracking Technique—0
Divergence Results and Convergence of a Variance Reduced Version of ADAM—0
Zeroth-Order Hard-Thresholding: Gradient Error vs. Expansivity—0
On Adaptivity in Non-stationary Stochastic Optimization With Bandit Feedback—0
Rieoptax: Riemannian Optimization in JAXCode0
Stochastic optimization on matrices and a graphon McKean-Vlasov limit—0
META-STORM: Generalized Fully-Adaptive Variance Reduced SGD for Unbounded Functions—0
Exploring the Algorithm-Dependent Generalization of AUPRC Optimization with List StabilityCode0
Feature-based Learning for Diverse and Privacy-Preserving Counterfactual ExplanationsCode0
Two-Tailed Averaging: Anytime, Adaptive, Once-in-a-While Optimal Weight Averaging for Better Generalization—0
Stochastic Gradient Descent Captures How Children Learn About PhysicsCode1
Stochastic Optimization of 3D Non-Cartesian Sampling Trajectory (SNOPY)—0
On the Theoretical Properties of Noise Correlation in Stochastic Optimization—0
Efficiency Ordering of Stochastic Gradient Descent—0
Private Stochastic Optimization With Large Worst-Case Lipschitz Parameter—0
Concealing Sensitive Samples against Gradient Leakage in Federated LearningCode0
Annealing Optimization for Progressive Learning with Stochastic ApproximationCode0
A risk measurement approach from risk-averse stochastic optimization of score functions—0
Practical Operator Sketching Framework for Accelerating Iterative Data-Driven Solutions in Inverse Problems—0
Minimax AUC Fairness: Efficient Algorithm with Provable ConvergenceCode0
Minimum Cost Adaptive Submodular Cover—0
ALS: Augmented Lagrangian Sketching Methods for Linear Systems—0
Near-Optimal Algorithms for Making the Gradient Small in Stochastic Minimax OptimizationCode0
Adaptive Learning Rates for Faster Stochastic Gradient Methods—0
Quantization enabled Privacy Protection in Decentralized Stochastic Optimization—0
SGEM: stochastic gradient with energy and momentumCode0
Formal guarantees for heuristic optimization algorithms used in machine learning—0
Show:102550
← PrevPage 9 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