How to trap a gradient flow

DOI10.1137/21M1397854MaRDI QIDQ6573775zbMATH OpenFDO

Authors Sébastien Bubeck, Dan Mikulincer

Publication date 17 July 2024

Published in SIAM Journal on Computing (Search for Journal in Brave)

zbMATH Keywords

non-convex optimizationgradient flowblack-box optimization

Mathematics Subject Classification ID

Nonconvex programming, global optimization (90C26) Interior-point methods (90C51)

Recommendations

• Lower bounds for finding stationary points I
• Lower bounds for finding stationary points II: first-order methods
• Lower bounds for non-convex stochastic optimization
• Gradient descent finds the cubic-regularized nonconvex Newton step
• Gradient Transformation Trajectory Following Algorithms for Determining Stationary Min-Max Saddle Points

Cites work

• scientific article; zbMATH DE number 3790208 (Why is no real title available?)
• Black-Box Complexity of Local Minimization
• Convex optimization: algorithms and complexity
• Introductory lectures on convex optimization. A basic course.
• Lower Bounds for Local Search by Quantum Arguments
• Lower bounds for finding stationary points I
• Nearest-neighbor walks with low predictability profile and percolation in \(2+\varepsilon\) dimensions
• New upper and lower bounds for randomized and quantum local search
• On parallel complexity of nonsmooth convex optimization
• On the quantum query complexity of local search in two and three dimensions
• Unpredictable paths and percolation

This page was built for publication: How to trap a gradient flow

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6573775)