Imagen de Portada

Improving the Worst-Case Bidirectional Communication Complexity for Nonconvex Distributed Optimization under Function Similarity

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Gruntkowska, Kaja, Tyurin, Alexander, Richtárik, Peter
Formato:	Preprint
Publicado:	2024
Materias:	Optimization and Control Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Freya PAGE: First Optimal Time Complexity for Large-Scale Nonconvex Finite-Sum Optimization with Heterogeneous Asynchronous Computations
por: Tyurin, Alexander, et al.
Publicado: (2024)

Tighter Performance Theory of FedExProx
por: Anyszka, Wojciech, et al.
Publicado: (2024)

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

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

Local LMO: Constrained Gradient Optimization via a Local Linear Minimization Oracle
por: Richtárik, Peter, et al.
Publicado: (2026)

Gluon: Making Muon & Scion Great Again! (Bridging Theory and Practice of LMO-based Optimizers for LLMs)
por: Riabinin, Artem, et al.
Publicado: (2025)

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

Drop-Muon: Update Less, Converge Faster
por: Gruntkowska, Kaja, et al.
Publicado: (2025)

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

Shadowheart SGD: Distributed Asynchronous SGD with Optimal Time Complexity Under Arbitrary Computation and Communication Heterogeneity
por: Tyurin, Alexander, et al.
Publicado: (2024)

Communication Compression for Byzantine Robust Learning: New Efficient Algorithms and Improved Rates
por: Rammal, Ahmad, et al.
Publicado: (2023)

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

Ringmaster ASGD: The First Asynchronous SGD with Optimal Time Complexity
por: Maranjyan, Artavazd, et al.
Publicado: (2025)

Broximal Alignment for Global Non-Convex Optimization
por: Gruntkowska, Kaja, et al.
Publicado: (2026)

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

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

Near-Optimal Convergence of Accelerated Gradient Methods under Generalized and $(L_0, L_1)$-Smoothness
por: Tyurin, Alexander
Publicado: (2025)

A Novel Unified Parametric Assumption for Nonconvex Optimization
por: Riabinin, Artem, et al.
Publicado: (2025)

Second-order Optimization under Heavy-Tailed Noise: Hessian Clipping and Sample Complexity Limits
por: Sadiev, Abdurakhmon, et al.
Publicado: (2025)

Correlated Quantization for Faster Nonconvex Distributed Optimization
por: Panferov, Andrei, et al.
Publicado: (2024)

Local SGD and Federated Averaging Through the Lens of Time Complexity
por: Fradin, Adrien, et al.
Publicado: (2025)

Proving the Limited Scalability of Centralized Distributed Optimization via a New Lower Bound Construction
por: Tyurin, Alexander
Publicado: (2025)

Scalable Distributed Stochastic Optimization via Bidirectional Compression: Beyond Pessimistic Limits
por: Begunov, Grigory, et al.
Publicado: (2026)

MARINA-P: Superior Performance in Non-smooth Federated Optimization with Adaptive Stepsizes
por: Sokolov, Igor, et al.
Publicado: (2024)

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

Gradient Descent as a Perceptron Algorithm: Understanding Dynamics and Implicit Acceleration
por: Tyurin, Alexander
Publicado: (2025)

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

Improved Sample Complexity for Private Nonsmooth Nonconvex Optimization
por: Kornowski, Guy, et al.
Publicado: (2024)

Rescaled Asynchronous SGD: Optimal Distributed Optimization under Data and System Heterogeneity
por: Mahran, Ammar, et al.
Publicado: (2026)

Improved Convergence Rates of Muon Optimizer for Nonconvex Optimization
por: Nagashima, Shuntaro, et al.
Publicado: (2026)

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

Ringleader ASGD: The First Asynchronous SGD with Optimal Time Complexity under Data Heterogeneity
por: Maranjyan, Artavazd, et al.
Publicado: (2025)

On the Complexity of Decentralized Smooth Nonconvex Finite-Sum Optimization
por: Luo, Luo, et al.
Publicado: (2022)

Decentralized Stochastic Nonconvex Optimization under the Relaxed Smoothness
por: Luo, Luo, et al.
Publicado: (2025)

On the Complexity of Finding Stationary Points in Nonconvex Simple Bilevel Optimization
por: Cao, Jincheng, et al.
Publicado: (2025)

Improved Complexity for Smooth Nonconvex Optimization: A Two-Level Online Learning Approach with Quasi-Newton Methods
por: Jiang, Ruichen, et al.
Publicado: (2024)

Near-Optimal Distributed Minimax Optimization under the Second-Order Similarity
por: Zhou, Qihao, et al.
Publicado: (2024)

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

Improving Online-to-Nonconvex Conversion for Smooth Optimization via Double Optimism
por: Patitucci, Francisco, et al.
Publicado: (2025)

GradSkip: Communication-Accelerated Local Gradient Methods with Better Computational Complexity
por: Maranjyan, Artavazd, et al.
Publicado: (2022)