One-dimensional system arising in stochastic gradient descent

DOI10.1017/apr.2020.10zbMath1480.60066arXiv1802.06760OpenAlexW3185282559MaRDI QIDQ5022277

Konstantinos Karatapanis

Publication date: 18 January 2022

Published in: Advances in Applied Probability (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1802.06760

zbMATH Keywords

stochastic differential equationssaddle pointsstochastic approximationsgradient descent

Mathematics Subject Classification ID

Newton-type methods (49M15) Strong limit theorems (60F15)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• An explicit bound for the Łojasiewicz exponent of real polynomials
• Nonconvergence to unstable points in urn models and stochastic approximations
• A survey of random processes with reinforcement
• A strong law for some generalized urn processes
• On the law of the iterated logarithm for martingales
• Statistical inference for model parameters in stochastic gradient descent
• Guaranteed Matrix Completion via Non-Convex Factorization
• Complete Dictionary Recovery Over the Sphere I: Overview and the Geometric Picture
• Recursive Stochastic Algorithms for Global Optimization in $\mathbb{R}^d $
• Acceleration of Stochastic Approximation by Averaging
• Finding approximate local minima faster than gradient descent
• When are Touchpoints Limits for Generalized Polya URNS?
• A Stochastic Approximation Method

This page was built for publication: One-dimensional system arising in stochastic gradient descent