Imagen de Portada

Stochastic Gradient Descent in Non-Convex Problems: Asymptotic Convergence with Relaxed Step-Size via Stopping Time Methods

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Jin, Ruinan, Cheng, Difei, Qiao, Hong, Shi, Xin, Liu, Shaodong, Zhang, Bo
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning Optimization and Control Probability 40G15 G.1.0
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Convergence Analysis of the Last Iterate in Distributed Stochastic Gradient Descent with Momentum
por: Cheng, Difei, et al.
Publicado: (2025)

Holistic Decision-Making in Stopping Problems: Emphasizing Psychological Aspects
por: Sofronov, Georgy, et al.
Publicado: (2026)

Stopping Times of Boundaries: Relaxation and Continuity
por: Soner, H. Mete, et al.
Publicado: (2023)

Projected Inventory Level Policies for Lost Sales Inventory Systems: Asymptotic Optimality in Two Regimes
por: van Jaarsveld, Willem, et al.
Publicado: (2021)

Convergence rates for Backward SDEs driven by Lévy processes
por: Liu, Chenguang, et al.
Publicado: (2024)

Optimal Stopping of BSDEs with Constrained Jumps and Related Double Obstacle PDEs
por: Perninge, Magnus
Publicado: (2024)

Asymptotic Optimality of Projected Inventory Level Policies for Lost Sales Inventory Systems with Large Leadtime and Penalty Cost
por: Moradi, Poulad, et al.
Publicado: (2025)

Convergence Analysis of Fractional Gradient Descent
por: Aggarwal, Ashwani
Publicado: (2023)

Almost Sure Convergence of Stochastic Approximation: An Interplay of Noise and Step Size
por: Nguyen, Quang Dinh Thien, et al.
Publicado: (2026)

The Last-Success Stopping Problem with Random Observation Times
por: Gnedin, Alexander, et al.
Publicado: (2022)

Maximal Counts in the Stopped Occupancy Problem
por: Gnedin, Alexander, et al.
Publicado: (2025)

Handbook of Convergence Theorems for (Stochastic) Gradient Methods
por: Garrigos, Guillaume, et al.
Publicado: (2023)

Controlling the Flow: Stability and Convergence for Stochastic Gradient Descent with Decaying Regularization
por: Kassing, Sebastian, et al.
Publicado: (2025)

Stochastic control with dividend payments and capital injections for Markov additive processes
por: Noba, Kei
Publicado: (2026)

Achieving Exponential Asymptotic Optimality in Average-Reward Restless Bandits without Global Attractor Assumption
por: Hong, Yige, et al.
Publicado: (2024)

Adaptive Stochastic Gradient Descent Ascent Algorithm for Nonconvex Minimax Problems with Decision-Dependent Distributions
por: Gao, Yan, et al.
Publicado: (2025)

Quantitative Convergence Rates for Stochastically Monotone Markov Chains
por: Kamihigashi, Takashi, et al.
Publicado: (2024)

Convergence Error Analysis of Reflected Gradient Langevin Dynamics for Globally Optimizing Non-Convex Constrained Problems
por: Sato, Kanji, et al.
Publicado: (2022)

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

Convergence Rate for the Last Iterate of Stochastic Gradient Descent Schemes
por: Hudiani, Marcel
Publicado: (2025)

Optimal Stopping for the Uniform Distribution
por: Gnedin, Alexander
Publicado: (2026)

Sum the Probabilities to $m$ and Stop
por: Derbazi, Zakaria
Publicado: (2024)

Stopping Times Occurring Simultaneously
por: Protter, Philip, et al.
Publicado: (2021)

Drift Control with Discretionary Stopping for a Diffusion
por: Beneš, Václav E., et al.
Publicado: (2024)

Stochastic Calculus via Stopping Derivatives
por: Simpson, Alex
Publicado: (2025)

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

An exit contract optimization problem
por: He, Xihao, et al.
Publicado: (2021)

On the limit theory of mean field optimal stopping with non-Markov dynamics and common noise
por: He, Xihao
Publicado: (2023)

Sensitivity of causal distributionally robust optimization
por: Jiang, Yifan, et al.
Publicado: (2024)

Learning operators on labelled conditional distributions with applications to mean field control of non exchangeable systems
por: Mekkaoui, Samy, et al.
Publicado: (2026)

Almost Perfect Shadow Prices
por: Mayerhofer, Eberhard
Publicado: (2024)

Stopping problems with an unknown state
por: Ekström, Erik, et al.
Publicado: (2022)

Stochastic control with self-exciting processes
por: Eyjolfsson, Heidar, et al.
Publicado: (2026)

Trust Region Algorithm for Stochastic Minimax Problems with Decision-Dependent Distributions
por: Gao, Yan, et al.
Publicado: (2025)

A Relaxation Method for Nonsmooth Nonlinear Optimization with Binary Constraints
por: Xiao, Lianghai, et al.
Publicado: (2026)

Stochastic Mirror Descent for Convex Optimization with Consensus Constraints
por: Borovykh, Anastasia, et al.
Publicado: (2022)

On Spectral Approach to the Synthesis of Shaping Filters
por: Rybakov, Konstantin A.
Publicado: (2025)

Asymptotic Convergence and Stability of Adaptive Gradient Methods in Smooth Non-convex Optimization
por: Jin, Ruinan, et al.
Publicado: (2026)

Non-Stationary Gradient Descent for Optimal Auto-Scaling in Serverless Platforms
por: Anselmi, Jonatha, et al.
Publicado: (2025)

Rearranged Stochastic Heat Equation: Ergodicity and Related Gradient Descent on ${\mathcal P}({\mathbb R})$
por: Delarue, François, et al.
Publicado: (2024)