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 151–200 of 1387 papers

TitleStatusHype
Revisiting LocalSGD and SCAFFOLD: Improved Rates and Missing Analysis—0
Boosting Adversarial Transferability through Augmentation in Hypothesis SpaceCode0
Preconditioners for the Stochastic Training of Neural Fields—0
DaCapo: Score Distillation as Stacked Bridge for Fast and High-quality 3D Editing—0
A Nearly Optimal Single Loop Algorithm for Stochastic Bilevel Optimization under Unbounded SmoothnessCode0
Nonconvex Stochastic Optimization under Heavy-Tailed Noises: Optimal Convergence without Gradient Clipping—0
A stochastic first-order method with multi-extrapolated momentum for highly smooth unconstrained optimization—0
Projected gradient methods for nonconvex and stochastic optimization: new complexities and auto-conditioned stepsizes—0
Bilevel Learning with Inexact Stochastic GradientsCode0
Memory-Efficient 4-bit Preconditioned Stochastic Optimization—0
AmCLR: Unified Augmented Learning for Cross-Modal RepresentationsCode0
Stochastic Gradient Descent Revisited—0
Equivariant Denoisers for Image Restoration—0
Fixed-Mean Gaussian Processes for Post-hoc Bayesian Deep LearningCode0
Offline Stochastic Optimization of Black-Box Objective Functions—0
Resilience-oriented Planning and Cost Allocation of Energy Storage Integrated with Soft Open Point Based on Resilience Insurance—0
Accelerated zero-order SGD under high-order smoothness and overparameterized regime—0
Problem-dependent convergence bounds for randomized linear gradient compression—0
On Reductions and Representations of Learning Problems in Euclidean Spaces—0
Complexity-Aware Training of Deep Neural Networks for Optimal Structure Discovery—0
Deep Generative Demand Learning for Newsvendor and Pricing—0
A Stochastic Optimization Framework for Private and Fair Learning From Decentralized DataCode0
Convergence Rate Analysis of LION—0
Effectively Leveraging Momentum Terms in Stochastic Line Search Frameworks for Fast Optimization of Finite-Sum ProblemsCode0
Movable Antenna-Aided Federated Learning with Over-the-Air Aggregation: Joint Optimization of Positioning, Beamforming, and User Selection—0
Two-Stage Stochastic Optimization for Low-Carbon Dispatch in a Combined Energy System—0
Asymptotic regularity of a generalised stochastic Halpern scheme with applications—0
Memory-Driven Metaheuristics: Improving Optimization Performance—0
Adaptive Consensus Gradients Aggregation for Scaled Distributed TrainingCode0
Forecasting Outside the Box: Application-Driven Optimal Pointwise Forecasts for Stochastic Optimization—0
Fair and Welfare-Efficient Constrained Multi-matchings under UncertaintyCode0
MESS+: Energy-Optimal Inferencing in Language Model Zoos with Service Level Guarantees—0
Towards Reliable Alignment: Uncertainty-aware RLHF—0
Dynamic Matching with Post-allocation Service and its Application to Refugee Resettlement—0
Stochastic Approximation with Unbounded Markovian Noise: A General-Purpose Theorem—0
Tuning-Free Coreset Markov Chain Monte Carlo via Hot DoGCode0
Survival Models: Proper Scoring Rule and Stochastic Optimization with Competing Risks—0
A quantitative Robbins-Siegmund theorem—0
Beyond Discretization: Learning the Optimal Solution PathCode0
From Gradient Clipping to Normalization for Heavy Tailed SGD—0
A Stochastic Approach to Bi-Level Optimization for Hyperparameter Optimization and Meta Learning—0
MindFlayer SGD: Efficient Parallel SGD in the Presence of Heterogeneous and Random Worker Compute Times—0
On the SAGA algorithm with decreasing step—0
SpaceMesh: A Continuous Representation for Learning Manifold Surface Meshes—0
Online Client Scheduling and Resource Allocation for Efficient Federated Edge Learning—0
Non-asymptotic convergence analysis of the stochastic gradient Hamiltonian Monte Carlo algorithm with discontinuous stochastic gradient with applications to training of ReLU neural networksCode0
Trust-Region Sequential Quadratic Programming for Stochastic Optimization with Random Models—0
On Broad-Beam Reflection for Dual-Polarized RIS-Assisted MIMO Systems—0
SplitVAEs: Decentralized scenario generation from siloed data for stochastic optimization problems—0
Variance-reduced first-order methods for deterministically constrained stochastic nonconvex optimization with strong convergence guarantees—0
Show:102550
← PrevPage 4 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