Cover Image

Convergence, Sticking and Escape: Stochastic Dynamics Near Critical Points in SGD

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Dudukalov, Dmitry, Logachov, Artem, Lotov, Vladimir, Prasolov, Timofei, Prokopenko, Evgeny, Tarasenko, Anton
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Probability
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Basic model for ranking microfinance institutions
by: Dudukalov, Dmitry, et al.
Published: (2025)

Central Limit Theorem on Symmetric Kullback-Leibler (KL) Divergence
by: Rojas, Helder, et al.
Published: (2024)

Convergence of SGD for Training Neural Networks with Sliced Wasserstein Losses
by: Tanguy, Eloi
Published: (2023)

Non-Asymptotic Convergence of Stochastic Iterative Algorithms: A Lyapunov Framework
by: Chen, Zaiwei, et al.
Published: (2026)

Error estimates between SGD with momentum and underdamped Langevin diffusion
by: Guillin, Arnaud, et al.
Published: (2024)

Effective continuous equations for adaptive SGD: a stochastic analysis view
by: Callisti, Luca, et al.
Published: (2025)

Implicit Compressibility of Overparametrized Neural Networks Trained with Heavy-Tailed SGD
by: Wan, Yijun, et al.
Published: (2023)

Convergent Stochastic Training of Attention and Understanding LoRA
by: Sun, Zhengkai, et al.
Published: (2026)

Decentralized Proximal Stochastic Gradient Langevin Dynamics
by: Islam, Mohammad Rafiqul, et al.
Published: (2026)

Weak Convergence Analysis of Online Neural Actor-Critic Algorithms
by: Lam, Samuel Chun-Hei, et al.
Published: (2024)

Minima and Critical Points of the Bethe Free Energy Are Invariant Under Deformation Retractions of Factor Graphs
by: Sergeant-Perthuis, Grégoire, et al.
Published: (2025)

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

ResNets of All Shapes and Sizes: Convergence of Training Dynamics in the Large-scale Limit
by: Chaintron, Louis-Pierre, et al.
Published: (2026)

Convergence of Two Time-Scale Stochastic Approximation: A Martingale Approach
by: Vidyasagar, Mathukumalli
Published: (2026)

Convergence of Actor-Critic Learning for Mean Field Games and Mean Field Control in Continuous Spaces
by: Fouque, Jean-Pierre, et al.
Published: (2025)

From Set Convergence to Pointwise Convergence: Finite-Time Guarantees for Average-Reward Q-Learning with Adaptive Stepsizes
by: Chen, Zaiwei, et al.
Published: (2025)

Stochastic Differential Equations models for Least-Squares Stochastic Gradient Descent
by: Schertzer, Adrien, et al.
Published: (2024)

Flatness-Aware Stochastic Gradient Langevin Dynamics
by: Bruno, Stefano, et al.
Published: (2025)

Exponential Convergence Guarantees for Iterative Markovian Fitting
by: Silveri, Marta Gentiloni, et al.
Published: (2025)

Stochastic Operator Network: A Stochastic Maximum Principle Based Approach to Operator Learning
by: Bausback, Ryan, et al.
Published: (2025)

Riemannian Langevin Dynamics: Strong Convergence of Geometric Euler-Maruyama Scheme
by: Zhan, Zhiyuan, et al.
Published: (2026)

Deep Learning for Computing Convergence Rates of Markov Chains
by: Qu, Yanlin, et al.
Published: (2024)

Convergence Analysis of Newton's Method for Neural Networks in the Overparameterized Limit
by: Riedl, Konstantin, et al.
Published: (2026)

Large Deviation Upper Bounds and Improved MSE Rates of Nonlinear SGD: Heavy-tailed Noise and Power of Symmetry
by: Armacki, Aleksandar, et al.
Published: (2024)

Characterizing Dynamical Stability of Stochastic Gradient Descent in Overparameterized Learning
by: Chemnitz, Dennis, et al.
Published: (2024)

Learning the Infinitesimal Generator of Stochastic Diffusion Processes
by: Kostic, Vladimir R., et al.
Published: (2024)

Structural and Convergence Analysis of Discrete-Time Denoising Diffusion Probabilistic Models
by: Nakano, Yumiharu
Published: (2024)

Random-Bridges as Stochastic Transports for Generative Models
by: Goria, Stefano, et al.
Published: (2025)

Convergence Analysis for General Probability Flow ODEs of Diffusion Models in Wasserstein Distances
by: Gao, Xuefeng, et al.
Published: (2024)

Wasserstein Convergence Guarantees for a General Class of Score-Based Generative Models
by: Gao, Xuefeng, et al.
Published: (2023)

Limit Theorems for Stochastic Gradient Descent with Infinite Variance
by: Blanchet, Jose, et al.
Published: (2024)

Partially Stochastic Infinitely Deep Bayesian Neural Networks
by: Calvo-Ordonez, Sergio, et al.
Published: (2024)

Approximating G(t)/GI/1 queues with deep learning
by: Sherzer, Eliran, et al.
Published: (2024)

Stabilizing Temporal Difference Learning via Implicit Stochastic Recursion
by: Kim, Hwanwoo, et al.
Published: (2025)

Flow Matching: Markov Kernels, Stochastic Processes and Transport Plans
by: Wald, Christian, et al.
Published: (2025)

Approximation to Deep Q-Network by Stochastic Delay Differential Equations
by: Lu, Jianya, et al.
Published: (2025)

Stochastic Scaling Limits and Synchronization by Noise in Deep Transformer Models
by: Agazzi, Andrea, et al.
Published: (2026)

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

Statistical Inference for Linear Functionals of Online SGD in High-dimensional Linear Regression
by: Agrawalla, Bhavya, et al.
Published: (2023)

Convergence of Unadjusted Langevin in High Dimensions: Delocalization of Bias
by: Chen, Yifan, et al.
Published: (2024)