Copertina

A dynamic view of some anomalous phenomena in SGD

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autore principale:	Borkar, Vivek Shripad
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Optimization and Control Machine Learning 62L20
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Stochastic approximation in non-markovian environments revisited
di: Borkar, Vivek Shripad
Pubblicazione: (2026)

Nonasymptotic Analysis of Stochastic Gradient Descent with the Richardson-Romberg Extrapolation
di: Sheshukova, Marina, et al.
Pubblicazione: (2024)

Improved High-Probability Bounds for the Temporal Difference Learning Algorithm via Exponential Stability
di: Samsonov, Sergey, et al.
Pubblicazione: (2023)

High-Order Error Bounds for Markovian LSA with Richardson-Romberg Extrapolation
di: Levin, Ilya, et al.
Pubblicazione: (2025)

High Probability Bounds for Stochastic Subgradient Schemes with Heavy Tailed Noise
di: Parletta, Daniela A., et al.
Pubblicazione: (2022)

A Short Survey of Averaging Techniques in Stochastic Gradient Methods
di: Lakshmanan, K.
Pubblicazione: (2026)

Global Convergence and Acceleration for Single Observation Gradient Free Optimization
di: Lauand, Caio Kalil, et al.
Pubblicazione: (2025)

Statistical inference for Linear Stochastic Approximation with Markovian Noise
di: Samsonov, Sergey, et al.
Pubblicazione: (2025)

An Iterative Bayesian Robbins--Monro Sequence
di: Liu, Siwei, et al.
Pubblicazione: (2025)

Improved Central Limit Theorem and Bootstrap Approximations for Linear Stochastic Approximation
di: Butyrin, Bogdan, et al.
Pubblicazione: (2025)

Gaussian Approximation and Multiplier Bootstrap for Polyak-Ruppert Averaged Linear Stochastic Approximation with Applications to TD Learning
di: Samsonov, Sergey, et al.
Pubblicazione: (2024)

Average-reward reinforcement learning in semi-Markov decision processes via relative value iteration
di: Yu, Huizhen, et al.
Pubblicazione: (2025)

Asynchronous Stochastic Approximation with Applications to Average-Reward Reinforcement Learning
di: Yu, Huizhen, et al.
Pubblicazione: (2024)

Stochastic Approximation with Two Time Scales: The General Case
di: Borkar, Vivek S
Pubblicazione: (2024)

When Does Dynamic Preconditioning Preserve the Polyak-Ruppert CLT? A Stabilization Threshold
di: An, Sunyoung, et al.
Pubblicazione: (2026)

A weak convergence approach to large deviations for stochastic approximations
di: Hult, Henrik, et al.
Pubblicazione: (2025)

Mini-Batch Covariance, Diffusion Limits, and Oracle Complexity in Stochastic Gradient Descent: A Sampling-Design Perspective
di: Zantedeschi, Daniel, et al.
Pubblicazione: (2026)

Revisiting Stochastic Approximation and Stochastic Gradient Descent
di: Karandikar, Rajeeva Laxman, et al.
Pubblicazione: (2025)

On the Rate of Gaussian Approximation for Linear Regression Problems
di: Khusainov, Marat, et al.
Pubblicazione: (2025)

Gaussian Approximation for Two-Timescale Linear Stochastic Approximation
di: Butyrin, Bogdan, et al.
Pubblicazione: (2025)

Stability and Sensitivity Analysis of Relative Temporal-Difference Learning: Extended Version
di: Sakha, Masoud S., et al.
Pubblicazione: (2026)

Optimistic Training and Convergence of Q-Learning -- Extended Version
di: Mehta, Prashant, et al.
Pubblicazione: (2026)

Sample Complexity of Policy Gradient for Log-Growth Control
di: Pan, Qiuhua, et al.
Pubblicazione: (2026)

Extremely Fast Convergence Rates for Extremum Seeking Control with Polyak-Ruppert Averaging
di: Lauand, Caio Kalil, et al.
Pubblicazione: (2022)

Convergence Rates for Stochastic Approximation: Biased Noise with Unbounded Variance, and Applications
di: Karandikar, Rajeeva L., et al.
Pubblicazione: (2023)

On-Average Stability of Multipass Preconditioned SGD and Effective Dimension
di: Vary, Simon, et al.
Pubblicazione: (2026)

Optimal control under unknown intensity with Bayesian learning
di: Baradel, Nicolas, et al.
Pubblicazione: (2024)

A Note on Stability in Asynchronous Stochastic Approximation without Communication Delays
di: Yu, Huizhen, et al.
Pubblicazione: (2023)

The ODE Method for Asymptotic Statistics in Stochastic Approximation and Reinforcement Learning
di: Borkar, Vivek, et al.
Pubblicazione: (2021)

Gaussian Approximation and Multiplier Bootstrap for Stochastic Gradient Descent
di: Sheshukova, Marina, et al.
Pubblicazione: (2025)

Cutting Some Slack for SGD with Adaptive Polyak Stepsizes
di: Gower, Robert M., et al.
Pubblicazione: (2022)

Stochastic Modified Flows for Riemannian Stochastic Gradient Descent
di: Gess, Benjamin, et al.
Pubblicazione: (2024)

Adaptive Stochastic Gradient Descents on Manifolds with an Application on Weighted Low-Rank Approximation
di: Yang, Peiqi, et al.
Pubblicazione: (2025)

Finite-Time Analysis of Projected Two-Time-Scale Stochastic Approximation
di: Bai, Yitao, et al.
Pubblicazione: (2026)

Sensitivity Analysis of the Consistency Assumption
di: Knaeble, Brian, et al.
Pubblicazione: (2025)

Branch and Bound to Assess Stability of Regression Coefficients in Uncertain Models
di: Knaeble, Brian, et al.
Pubblicazione: (2024)

A Sequential Testing Problem with Signal Control
di: Campbell, Steven, et al.
Pubblicazione: (2025)

Exponential convergence rates for momentum stochastic gradient descent in the overparametrized setting
di: Gess, Benjamin, et al.
Pubblicazione: (2023)

Adam Improves Muon: Adaptive Moment Estimation with Orthogonalized Momentum
di: Zhang, Minxin, et al.
Pubblicazione: (2026)

Stochastic optimal transport in Banach Spaces for regularized estimation of multivariate quantiles
di: Bercu, Bernard, et al.
Pubblicazione: (2023)