Cover Image

Cutting Some Slack for SGD with Adaptive Polyak Stepsizes

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Gower, Robert M., Blondel, Mathieu, Gazagnadou, Nidham, Pedregosa, Fabian
Format:	Preprint
Published:	2022
Subjects:	Machine Learning Optimization and Control 90C53, 74S60, 90C06, 62L20, 68W20, 15B52, 65Y20, 68W40 G.1.6
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Analysis of an Idealized Stochastic Polyak Method and its Application to Black-Box Model Distillation
by: Gower, Robert M., et al.
Published: (2025)

MoMo: Momentum Models for Adaptive Learning Rates
by: Schaipp, Fabian, et al.
Published: (2023)

Stable gradient-adjusted root mean square propagation on least squares problem
by: Li, Runze, et al.
Published: (2024)

Stochastic versus Deterministic in Stochastic Gradient Descent
by: Li, Runze, et al.
Published: (2025)

Structured Sketching for Linear Systems
by: Brust, Johannes J, et al.
Published: (2024)

Federated Learning with Convex Global and Local Constraints
by: He, Chuan, et al.
Published: (2023)

Distributed Computing for Huge-Scale Aggregative Convex Programming
by: Tao, Luoyi
Published: (2026)

Classification by Separating Hypersurfaces: An Entropic Approach
by: Arratia, Argimiro, et al.
Published: (2025)

Dimension-free estimators of gradients of functions with(out) non-independent variables
by: Lamboni, Matieyendou
Published: (2025)

Have ASkotch: A Neat Solution for Large-scale Kernel Ridge Regression
by: Rathore, Pratik, et al.
Published: (2024)

Enhancing Diversity in Multi-objective Feature Selection
by: Miyandoab, Sevil Zanjani, et al.
Published: (2024)

Adaptive monotonicity testing in sublinear time
by: Li, Housen, et al.
Published: (2025)

On the boundedness of the sequence generated by minibatch stochastic gradient descent
by: Bauschke, Heinz H., et al.
Published: (2025)

CompressedScaffnew: The First Theoretical Double Acceleration of Communication from Local Training and Compression in Distributed Optimization
by: Condat, Laurent, et al.
Published: (2022)

Optimal Online Bipartite Matching in Degree-2 Graphs
by: Bhangale, Amey, et al.
Published: (2025)

Stochastic trace estimation for parameter-dependent matrices applied to spectral density approximation
by: Matti, Fabio, et al.
Published: (2025)

Exact recovery for seeded graph matching
by: Fraiman, Nicolas, et al.
Published: (2026)

Subspace-constrained randomized coordinate descent for linear systems with good low-rank matrix approximations
by: Lok, Jackie, et al.
Published: (2025)

Acceleration and restart for the randomized Bregman-Kaczmarz method
by: Tondji, Lionel, et al.
Published: (2023)

Some Remarks on the Optimal Level of Randomization in Global Optimization
by: Theodosopoulos, Ted
Published: (2004)

A New Algorithm for Computing Integer Hulls of 2D Polyhedral Sets
by: Mukherjee, Chirantan
Published: (2025)

Primal-Dual Coordinate Descent for Nonconvex-Nonconcave Saddle Point Problems Under the Weak MVI Assumption
by: Walwil, Iyad, et al.
Published: (2025)

A Heuristic Alternating Direction Method of Multipliers Framework for Distributed and Centralized Tree-Constrained Optimization: Applications to Hop-Constrained Spanning Tree Multicommodity Flow Design
by: Mokhtari, Yacine
Published: (2025)

Efficient Multi-Processor Scheduling in Increasingly Realistic Models
by: Papp, Pál András, et al.
Published: (2024)

Parallelization Strategies for the Randomized Kaczmarz Algorithm on Large-Scale Dense Systems
by: Ferreira, Inês, et al.
Published: (2024)

Nature-Inspired Algorithms in Optimization: Introduction, Hybridization and Insights
by: Yang, Xin-She
Published: (2023)

RA-DCA: A Randomized Active-Set DCA for Directional Stationarity in Max-Structured DC Programs
by: Niu, Yi-Shuai
Published: (2026)

Correcting the Foundational Analysis of Karp--Vazirani--Vazirani (STOC 1990): A Rigorous Revision of the $1-1/e$ Upper Bound
by: Xu, Pan
Published: (2025)

Weighted domination models and randomized heuristics
by: Dijkstra, Lukas, et al.
Published: (2022)

Communication Compression for Distributed Learning without Control Variates
by: Ortega, Tomas, et al.
Published: (2024)

Communication Compression for Distributed Learning with Aggregate and Server-Guided Feedback
by: Ortega, Tomas, et al.
Published: (2025)

Quantized and Asynchronous Federated Learning
by: Ortega, Tomas, et al.
Published: (2024)

Decentralized Parameter-Free Online Learning with Compressed Gossip
by: Ortega, Tomas, et al.
Published: (2026)

Decentralized Parameter-Free Online Learning
by: Ortega, Tomas, et al.
Published: (2025)

Multi-Party Multi-Objective Optimization as Consensus Search: Runtime Analysis of Cross-Party Recombination
by: Fang, Xiaolei, et al.
Published: (2026)

An accelerated randomized Bregman-Kaczmarz method for strongly convex linearly constraint optimization
by: Tondji, Lionel, et al.
Published: (2025)

General Constrained Matrix Optimization
by: Garner, Casey, et al.
Published: (2024)

Spectrally Constrained Optimization
by: Garner, Casey, et al.
Published: (2023)

Distributed Computing for Huge-Scale Linear Programming
by: Tao, Luoyi
Published: (2024)

Decentralized Optimization in Networks with Arbitrary Delays
by: Ortega, Tomas, et al.
Published: (2024)