Imagen de Portada

Revisiting Stochastic Proximal Point Methods: Generalized Smoothness and Similarity

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Tovmasyan, Zhirayr, Malinovsky, Grigory, Condat, Laurent, Richtárik, Peter
Formato:	Preprint
Publicado:	2025
Materias:	Optimization and Control
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Stochastic Proximal Point Methods for Monotone Inclusions under Expected Similarity
por: Sadiev, Abdurakhmon, et al.
Publicado: (2024)

The Stochastic Multi-Proximal Method for Nonsmooth Optimization
por: Condat, Laurent, et al.
Publicado: (2025)

TAMUNA: Doubly Accelerated Distributed Optimization with Local Training, Compression, and Partial Participation
por: Condat, Laurent, et al.
Publicado: (2023)

Rennala MVR: Improved Time Complexity for Parallel Stochastic Optimization via Momentum-Based Variance Reduction
por: Tovmasyan, Zhirayr, et al.
Publicado: (2026)

A Simple Linear Convergence Analysis of the Point-SAGA Algorithm
por: Condat, Laurent, et al.
Publicado: (2024)

Convergence Analysis of the PAGE Stochastic Algorithm for Weakly Convex Finite-Sum Optimization
por: Condat, Laurent, et al.
Publicado: (2025)

Error Feedback for Muon and Friends
por: Gruntkowska, Kaja, et al.
Publicado: (2025)

A Unified Theory of Stochastic Proximal Point Methods without Smoothness
por: Richtárik, Peter, et al.
Publicado: (2024)

A Unified Primal-Dual Recipe for Accelerating Three-Operator Splitting Methods
por: Sadiev, Abdurakhmon, et al.
Publicado: (2026)

Tight Lower Bounds and Optimal Algorithms for Stochastic Nonconvex Optimization with Heavy-Tailed Noise
por: Fradin, Adrien, et al.
Publicado: (2025)

A Nesterov-Accelerated Primal-Dual Splitting Algorithm for Convex Nonsmooth Optimization
por: Condat, Laurent, et al.
Publicado: (2026)

Methods with Local Steps and Random Reshuffling for Generally Smooth Non-Convex Federated Optimization
por: Demidovich, Yury, et al.
Publicado: (2024)

BiCoLoR: Communication-Efficient Optimization with Bidirectional Compression and Local Training
por: Condat, Laurent, et al.
Publicado: (2026)

First Provable Guarantees for Practical Private FL: Beyond Restrictive Assumptions
por: Shulgin, Egor, et al.
Publicado: (2025)

LoCoDL: Communication-Efficient Distributed Learning with Local Training and Compression
por: Condat, Laurent, et al.
Publicado: (2024)

Sparse-ProxSkip: Accelerated Sparse-to-Sparse Training in Federated Learning
por: Meinhardt, Georg, et al.
Publicado: (2024)

Speeding up Stochastic Proximal Optimization in the High Hessian Dissimilarity Setting
por: Gasanov, Elnur, et al.
Publicado: (2024)

Stabilized Proximal Point Method via Trust Region Control
por: Li, Hanmin, et al.
Publicado: (2026)

MAST: Model-Agnostic Sparsified Training
por: Demidovich, Yury, et al.
Publicado: (2023)

Byzantine Robustness and Partial Participation Can Be Achieved at Once: Just Clip Gradient Differences
por: Malinovsky, Grigory, et al.
Publicado: (2023)

Improved Convergence in Parameter-Agnostic Error Feedback through Momentum
por: Sadiev, Abdurakhmon, et al.
Publicado: (2025)

The Ball-Proximal (="Broximal") Point Method: a New Algorithm, Convergence Theory, and Applications
por: Gruntkowska, Kaja, et al.
Publicado: (2025)

SPAM: Stochastic Proximal Point Method with Momentum Variance Reduction for Non-convex Cross-Device Federated Learning
por: Karagulyan, Avetik, et al.
Publicado: (2024)

Byzantine-Robust and Differentially Private Federated Optimization under Weaker Assumptions
por: Islamov, Rustem, et al.
Publicado: (2026)

Non-Euclidean Broximal Point Method: A Blueprint for Geometry-Aware Optimization
por: Gruntkowska, Kaja, et al.
Publicado: (2025)

On the Optimal Time Complexities in Decentralized Stochastic Asynchronous Optimization
por: Tyurin, Alexander, et al.
Publicado: (2024)

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

Randomized Asymmetric Chain of LoRA: The First Meaningful Theoretical Framework for Low-Rank Adaptation
por: Malinovsky, Grigory, et al.
Publicado: (2024)

Stochastic Bregman Proximal Gradient Method Revisited: Kernel Conditioning and Painless Variance Reduction
por: Zhang, Junyu
Publicado: (2024)

Inexact Accelerated Proximal Gradient Method Revisit: An Economical Variant via Shadow Points
por: Yang, Lei, et al.
Publicado: (2025)

Achieving Linear Speedup with ProxSkip in Distributed Stochastic Optimization
por: Guo, Luyao, et al.
Publicado: (2023)

Smoothed Proximal Lagrangian Method for Nonlinear Constrained Programs
por: Pu, Wenqiang, et al.
Publicado: (2024)

Bregman Proximal Method for Efficient Communications under Similarity
por: Beznosikov, Aleksandr, et al.
Publicado: (2023)

Near-Linear Time Projection onto the $\ell_{1,\infty}$ Ball; Application to Sparse Autoencoders
por: Perez, Guillaume, et al.
Publicado: (2023)

Improving the Worst-Case Bidirectional Communication Complexity for Nonconvex Distributed Optimization under Function Similarity
por: Gruntkowska, Kaja, et al.
Publicado: (2024)

A Proximal Method for Composite Optimization with Smooth and Convex Components
por: Uzun, Samet, et al.
Publicado: (2025)

Generalized Stochastic Gradient Descent with Momentum Methods for Smooth Optimization
por: Wang, Zimeng, et al.
Publicado: (2026)

Convergence of the Iterates of the Stochastic Proximal Gradient Method
por: Madariaga, Javier I.
Publicado: (2026)

A Computation and Communication Efficient Method for Distributed Nonconvex Problems in the Partial Participation Setting
por: Tyurin, Alexander, et al.
Publicado: (2022)

Smoothing Accelerated Proximal Gradient Method with Backtracking for Nonsmooth Multiobjective Optimization
por: Chengzhi, Huang
Publicado: (2025)