Imagen de Portada

Gradient-free algorithm for saddle point problems under overparametrization

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Statkevich, Ekaterina, Bondar, Sofiya, Dvinskikh, Darina, Gasnikov, Alexander, Lobanov, Aleksandr
Formato:	Preprint
Publicado:	2024
Materias:	Optimization and Control
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Randomized gradient-free methods in convex optimization
por: Gasnikov, Alexander, et al.
Publicado: (2022)

Accelerated zero-order SGD under high-order smoothness and overparameterized regime
por: Bychkov, Georgii, et al.
Publicado: (2024)

About some works of Boris Polyak on convergence of gradient methods and their development
por: Ablaev, Seydamet, et al.
Publicado: (2023)

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

Accelerated Zero-Order SGD Method for Solving the Black Box Optimization Problem under "Overparametrization" Condition
por: Lobanov, Aleksandr, et al.
Publicado: (2023)

Power of Generalized Smoothness in Stochastic Convex Optimization: First- and Zero-Order Algorithms
por: Lobanov, Aleksandr, et al.
Publicado: (2025)

Linear Convergence Rate in Convex Setup is Possible! Gradient Descent Method Variants under $(L_0,L_1)$-Smoothness
por: Lobanov, Aleksandr, et al.
Publicado: (2024)

Decentralized Distributed Optimization for Saddle Point Problems
por: Rogozin, Alexander, et al.
Publicado: (2021)

Acceleration Exists! Optimization Problems When Oracle Can Only Compare Objective Function Values
por: Lobanov, Aleksandr, et al.
Publicado: (2024)

The Black-Box Optimization Problem: Zero-Order Accelerated Stochastic Method via Kernel Approximation
por: Lobanov, Aleksandr, et al.
Publicado: (2023)

Nesterov's method of dichotomy via Order Oracle: The problem of optimizing a two-variable function on a square
por: Chervonenkis, Boris, et al.
Publicado: (2024)

Stochastic Optimization and Data Science
por: Avetisyan, Arutyun, et al.
Publicado: (2026)

The Mirror-Prox Sliding Method for Non-smooth decentralized saddle-point problems
por: Kuruzov, Ilya, et al.
Publicado: (2022)

Improved Iteration Complexity in Black-Box Optimization Problems under Higher Order Smoothness Function Condition
por: Lobanov, Aleksandr
Publicado: (2024)

Avoiding Bias in Clipped SGD for Overparameterized Models under Generalized Smoothness
por: Lobanov, Aleksandr, et al.
Publicado: (2026)

Wall-Clock Complexity for Zeroth-Order Optimization with Tunable Oracle Fidelity
por: Suvorikova, Alexandra, et al.
Publicado: (2026)

Local SGD for Near-Quadratic Problems: Improving Convergence under Unconstrained Noise Conditions
por: Sadchikov, Andrey, et al.
Publicado: (2024)

Accelerated Stochastic Gradient Method with Applications to Consensus Problem in Markov-Varying Networks
por: Solodkin, Vladimir, et al.
Publicado: (2024)

Gradient-Free Approaches is a Key to an Efficient Interaction with Markovian Stochasticity
por: Prokhorov, Boris, et al.
Publicado: (2026)

Median Clipping for Zeroth-order Non-Smooth Convex Optimization and Multi-Armed Bandit Problem with Heavy-tailed Symmetric Noise
por: Kornilov, Nikita, et al.
Publicado: (2024)

An inexact golden ratio primal-dual algorithm with linesearch step for a saddle point problem
por: Fang, Changjie, et al.
Publicado: (2024)

Adaptive primal dual hybrid gradient algorithms based on average spectrum for saddle point problems
por: Xu, Shengjie, et al.
Publicado: (2026)

Non-ergodic convergence rate of an inertial accelerated primal-dual algorithm for saddle point problems
por: He, X., et al.
Publicado: (2023)

First-order algorithms for robust optimization problems via convex-concave saddle-point Lagrangian reformulation
por: Postek, Krzysztof, et al.
Publicado: (2021)

Optimal Analysis of Method with Batching for Monotone Stochastic Finite-Sum Variational Inequalities
por: Pichugin, Alexander, et al.
Publicado: (2024)

A convex combination based primal-dual algorithm with linesearch for general convex-concave saddle point problems
por: Chang, Xiaokai, et al.
Publicado: (2024)

Extragradient Sliding for Composite Non-Monotone Variational Inequalities
por: Emelyanov, Roman, et al.
Publicado: (2024)

Accelerated Methods with Compression for Horizontal and Vertical Federated Learning
por: Stanko, Sergey, et al.
Publicado: (2024)

Activations and Gradients Compression for Model-Parallel Training
por: Rudakov, Mikhail, et al.
Publicado: (2024)

ODE approximation for the Adam algorithm: General and overparametrized setting
por: Dereich, Steffen, et al.
Publicado: (2025)

Method with Batching for Stochastic Finite-Sum Variational Inequalities in Non-Euclidean Setting
por: Pichugin, Alexander, et al.
Publicado: (2024)

Stochastic Frank-Wolfe: Unified Analysis and Zoo of Special Cases
por: Nazykov, Ruslan, et al.
Publicado: (2024)

Avoiding strict saddle points of nonconvex regularized problems
por: Bai, Luwei, et al.
Publicado: (2024)

Defining Lyapunov functions as the solution of a performance estimation saddle point problem
por: Fercoq, Olivier
Publicado: (2024)

Proximal gradient descent on the smoothed duality gap to solve saddle point problems
por: Fercoq, Olivier
Publicado: (2025)

Escaping saddle points without Lipschitz smoothness: the power of nonlinear preconditioning
por: Bodard, Alexander, et al.
Publicado: (2025)

On quasi-convex smooth optimization problems by a comparison oracle
por: Gasnikov, A. V., et al.
Publicado: (2024)

A Parameter-free Decentralized Algorithm for Composite Convex Optimization
por: Chen, Xiaokai, et al.
Publicado: (2025)

Optimal Data Splitting in Distributed Optimization for Machine Learning
por: Medyakov, Daniil, et al.
Publicado: (2024)

Adaptive Regularized Newton Method with Inexact Hessian
por: Shestakov, Aleksandr, et al.
Publicado: (2025)