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 1351–1387 of 1387 papers

TitleStatusHype
DISTRIBUTIONALLY ROBUST NEURAL NETWORKS FOR GROUP SHIFTS ON THE IMPORTANCE OF REGULARIZATION FOR WORST-CASE GENERALIZATION—0
Distributionally Robust Optimization with Correlated Data from Vector Autoregressive Processes—0
Distributionally Time-Varying Online Stochastic Optimization under Polyak-Łojasiewicz Condition with Application in Conditional Value-at-Risk Statistical Learning—0
Distribution-Dependent Analysis of Gibbs-ERM Principle—0
Distribution free M-estimation—0
Divergence Results and Convergence of a Variance Reduced Version of ADAM—0
Discontinuous Computation Offloading for Energy-Efficient Mobile Edge Computing—0
Does Momentum Help? A Sample Complexity Analysis—0
Don't Forget Your Teacher: A Corrective Reinforcement Learning Framework—0
A Deep Learning Perspective on Network Routing—0
Doubly stochastic large scale kernel learning with the empirical kernel map—0
Doubly-stochastic mining for heterogeneous retrieval—0
Stochastic Model Pruning via Weight Dropping Away and Back—0
DS-FACTO: Doubly Separable Factorization Machines—0
Dual Averaging for Distributed Optimization: Convergence Analysis and Network Scaling—0
Dual Averaging is Surprisingly Effective for Deep Learning Optimization—0
Dual coordinate solvers for large-scale structural SVMs—0
Dual Iterative Hard Thresholding: From Non-convex Sparse Minimization to Non-smooth Concave Maximization—0
Dual Stochastic Natural Gradient Descent and convergence of interior half-space gradient approximations—0
Dyna: A Method of Momentum for Stochastic Optimization—0
Dynamically Learned Test-Time Model Routing in Language Model Zoos with Service Level Guarantees—0
Dynamic Edge Computing empowered by Reconfigurable Intelligent Surfaces—0
Dynamic Feature Selection for Efficient and Interpretable Human Activity Recognition—0
Dynamic Matching with Post-allocation Service and its Application to Refugee Resettlement—0
Dynamic Resource Optimization for Decentralized Estimation in Energy Harvesting IoT Networks—0
Minimizing the AoI in Resource-Constrained Multi-Source Relaying Systems: Dynamic and Learning-based Scheduling—0
Dynamic Scheduling for Vehicle-to-Vehicle Communications Enhanced Federated Learning—0
Dynamic Stochastic Approximation for Multi-stage Stochastic Optimization—0
Dynamic Trajectory and Offloading Control of UAV-enabled MEC under User Mobility—0
Fair Incentives for Repeated Engagement—0
Eco-Driving Control of Connected and Automated Vehicles using Neural Network based Rollout—0
Effective Blind Source Separation Based on the Adam Algorithm—0
Effect of Random Learning Rate: Theoretical Analysis of SGD Dynamics in Non-Convex Optimization via Stationary Distribution—0
Efficiency Ordering of Stochastic Gradient Descent—0
Efficient Debiased Evidence Estimation by Multilevel Monte Carlo Sampling—0
Efficient Distributed SGD with Variance Reduction—0
Efficient Globally Convergent Stochastic Optimization for Canonical Correlation Analysis—0
Show:102550
← PrevPage 28 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