conftrace_

stochastic approximation

101 papers

Explore in graph

Also known as

SA

Co-occurring keywords

convergence rate (607) reinforcement learning (4352) temporal difference learning (149) markov chain (207) finite-time analysis (31) convergence analysis (395) markov decision process (790) convex optimization (1321) online learning (1777) policy evaluation (115)

Papers

Beyond Worst-Case Analysis in Stochastic Approximation: Moment Estimation Improves Instance Complexity ICML 2022
Statistical inference with implicit SGD: proximal Robbins-Monro vs. Polyak-Ruppert ICML 2022
Asymptotic Study of Stochastic Adaptive Algorithms in Non-convex Landscape JMLR 2022
A Single-timescale Analysis for Stochastic Approximation with Multiple Coupled Sequences NIPS 2022
Mirror Descent Strikes Again: Optimal Stochastic Convex Optimization under Infinite Noise Variance COLT 2022
Optimal and instance-dependent guarantees for Markovian linear stochastic approximation COLT 2022
Online Deep Equilibrium Learning for Regularization by Denoising NIPS 2022
Smooth Fictitious Play in Stochastic Games with Perturbed Payoffs and Unknown Transitions NIPS 2022
A Statistical Online Inference Approach in Averaged Stochastic Approximation NIPS 2022
Gradient Temporal Difference with Momentum: Stability and Convergence AAAI 2022
Global Optimality and Finite Sample Analysis of Softmax Off-Policy Actor Critic under State Distribution Mismatch JMLR 2022
State Dependent Performative Prediction with Stochastic Approximation AISTATS 2022
Asymptotic Behaviors of Projected Stochastic Approximation: A Jump Diffusion Perspective NIPS 2022
The Dynamics of Riemannian Robbins-Monro Algorithms COLT 2022
On Riemannian Stochastic Approximation Schemes with Fixed Step-Size AISTATS 2021
Robust Reinforcement Learning using Least Squares Policy Iteration with Provable Performance Guarantees ICML 2021
Fast Learning for Renewal Optimization in Online Task Scheduling JMLR 2021
Stochastic Approximation for Online Tensorial Independent Component Analysis COLT 2021
On the Stability of Random Matrix Product with Markovian Noise: Application to Linear Stochastic Approximation and TD Learning COLT 2021
Logical Team Q-learning: An approach towards factored policies in cooperative MARL AISTATS 2021
An Inertial Newton Algorithm for Deep Learning JMLR 2021
Nonlinear Two-Time-Scale Stochastic Approximation: Convergence and Finite-Time Performance L4DC 2021
Kernel Distributionally Robust Optimization: Generalized Duality Theorem and Stochastic Approximation AISTATS 2021
A Law of Iterated Logarithm for Multi-Agent Reinforcement Learning NIPS 2021
Convergence Properties of Stochastic Hypergradients AISTATS 2021