Stochastic modified flows for Riemannian stochastic gradient descent

Benjamin Gess, Nimit Rana, Sebastian Kassing

Publication date: 8 January 2025

Published in: SIAM Journal on Control and Optimization (Search for Journal in Brave)

zbMATH Keywords

Could not fetch data.

Mathematics Subject Classification ID

Numerical mathematical programming methods (65K05) Applications of Markov chains and discrete-time Markov processes on general state spaces (social mobility, learning theory, industrial processes, etc.) (60J20) Stochastic approximation (62L20) Diffusion processes and stochastic analysis on manifolds (58J65)

Cites Work

Title not available (Why is that?)
Title not available (Why is that?)
Title not available (Why is that?)
Title not available (Why is that?)
Title not available (Why is that?)
Stochastic partial differential equations: an introduction
Fisher information distance: a geometrical reading
Properties at infinity of diffusion semigroups and stochastic flows via weak uniform covers
Strong \(p\)-completeness of stochastic differential equations and the existence of smooth flows on noncompact manifolds
On the diffusion approximation of nonconvex stochastic gradient descent
Existence, uniqueness and regularity of the projection onto differentiable manifolds
Uniform-in-time weak error analysis for stochastic gradient descent algorithms via diffusion approximation
Semigroups of stochastic gradient descent and online principal component analysis: properties and diffusion approximations
Stochastic approximation on Riemannian manifolds
Cooling down stochastic differential equations: Almost sure convergence
Quadratic optimization with orthogonality constraint: explicit Łojasiewicz exponent and linear convergence of retraction-based line-search and stochastic variance-reduced gradient methods
Normally hyperbolic invariant manifolds. The noncompact case
Stochastic analysis on manifolds
Projection-like Retractions on Matrix Manifolds
Cylindrical Wiener Processes
The central limit problem for geodesic random walks
The Geometry of Algorithms with Orthogonality Constraints
Gradient algorithms for principal component analysis
An Introduction to Optimization on Smooth Manifolds
Stochastic Equations in Infinite Dimensions
Stochastic Gradient Descent on Riemannian Manifolds
Lie groups
On minimal representations of shallow ReLU networks
A Systematic Approach to Lyapunov Analyses of Continuous-Time Models in Convex Optimization
Stochastic gradient descent with noise of machine learning type. II: Continuous time analysis
Robust implicit regularization via weight normalization
On uniform-in-time diffusion approximation for stochastic gradient descent
On closed-form expressions for the Fisher-Rao distance

This page was built for publication: Stochastic modified flows for Riemannian stochastic gradient descent

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6658239)