Image de couverture de livre

Advancing the lower bounds: An accelerated, stochastic, second-order method with optimal adaptation to inexactness

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Agafonov, Artem, Kamzolov, Dmitry, Gasnikov, Alexander, Kavis, Ali, Antonakopoulos, Kimon, Cevher, Volkan, Takáč, Martin
Format:	Preprint
Publié:	2023
Sujets:	Optimization and Control
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Exploiting higher-order derivatives in convex optimization methods
par: Kamzolov, Dmitry, et autres
Publié: (2022)

OPTAMI: Global Superlinear Convergence of High-order Methods
par: Kamzolov, Dmitry, et autres
Publié: (2024)

Universal Gradient Methods for Stochastic Convex Optimization
par: Rodomanov, Anton, et autres
Publié: (2024)

Decentralized Inexact Cubic Newton Method with Consensus Procedure
par: Agafonov, Artem, et autres
Publié: (2026)

Exploring Jacobian Inexactness in Second-Order Methods for Variational Inequalities: Lower Bounds, Optimal Algorithms and Quasi-Newton Approximations
par: Agafonov, Artem, et autres
Publié: (2024)

AdaBatchGrad: Combining Adaptive Batch Size and Adaptive Step Size
par: Ostroukhov, Petr, et autres
Publié: (2024)

Simple Stepsize for Quasi-Newton Methods with Global Convergence Guarantees
par: Agafonov, Artem, et autres
Publié: (2025)

Lower and upper bounds of the convergence rate of gradient methods with composite noise in gradient
par: Vasin, Artem, et autres
Publié: (2026)

Constrained Stochastic Spectral Preconditioning Converges for Nonconvex Objectives
par: Oikonomidis, Konstantinos, et autres
Publié: (2026)

Training Deep Learning Models with Norm-Constrained LMOs
par: Pethick, Thomas, et autres
Publié: (2025)

Adaptive Regularized Newton Method with Inexact Hessian
par: Shestakov, Aleksandr, et autres
Publié: (2025)

Cubic Regularized Newton Method with Variance Reduction for Finite-sum Non-convex Problems
par: Pasechnyuk-Vilensky, Dmitry, et autres
Publié: (2025)

Layer-wise Quantization for Quantized Optimistic Dual Averaging
par: Nguyen, Anh Duc, et autres
Publié: (2025)

Gradient directions and relative inexactness in optimization and machine learning
par: Vasin, Artem
Publié: (2024)

An adaptively inexact first-order method for bilevel optimization with application to hyperparameter learning
par: Salehi, Mohammad Sadegh, et autres
Publié: (2023)

SANIA: Polyak-type Optimization Framework Leads to Scale Invariant Stochastic Algorithms
par: Abdukhakimov, Farshed, et autres
Publié: (2023)

An inexact $q$-order regularized proximal Newton method for nonconvex composite optimization
par: Liu, Ruyu, et autres
Publié: (2023)

An inexact Bregman proximal point method and its acceleration version for unbalanced optimal transport
par: Chen, Xiang, et autres
Publié: (2024)

Linear Convergence Rate in Convex Setup is Possible! Gradient Descent Method Variants under $(L_0,L_1)$-Smoothness
par: Lobanov, Aleksandr, et autres
Publié: (2024)

$ψ$DAG: Projected Stochastic Approximation Iteration for DAG Structure Learning
par: Ziu, Klea, et autres
Publié: (2024)

Universal methods for variational inequalities: deterministic and stochastic cases
par: Klimza, Anton, et autres
Publié: (2024)

The inexact power augmented Lagrangian method for constrained nonconvex optimization
par: Bodard, Alexander, et autres
Publié: (2024)

Stochastic Gradient Methods with Preconditioned Updates
par: Sadiev, Abdurakhmon, et autres
Publié: (2022)

On the Generalization of Stochastic Gradient Descent with Momentum
par: Ramezani-Kebrya, Ali, et autres
Publié: (2018)

Improving SAM Requires Rethinking its Optimization Formulation
par: Xie, Wanyun, et autres
Publié: (2024)

Similarity, Compression and Local Steps: Three Pillars of Efficient Communications for Distributed Variational Inequalities
par: Beznosikov, Aleksandr, et autres
Publié: (2023)

A unified framework for inexact adaptive stepsizes in the gradient methods, the conjugate gradient methods and the quasi-Newton methods for strictly convex quadratic optimization
par: Liu, Zexian
Publié: (2026)

Proximal gradient methods with inexact oracle of degree q for composite optimization
par: Nabou, Yassine, et autres
Publié: (2024)

An inexact variable metric proximal linearization method for composite optimization on manifolds
par: He, Hao, et autres
Publié: (2025)

An augmented Lagrangian trust-region method with inexact gradient evaluations to accelerate constrained optimization problems using model hyperreduction
par: Wen, Tianshu, et autres
Publié: (2024)

Strengthening the finite characterizations of smooth min-max games
par: Krivchenko, Valery, et autres
Publié: (2026)

Adaptive and Optimal Second-order Optimistic Methods for Minimax Optimization
par: Jiang, Ruichen, et autres
Publié: (2024)

Randomized gradient-free methods in convex optimization
par: Gasnikov, Alexander, et autres
Publié: (2022)

Nesterov's method of dichotomy via Order Oracle: The problem of optimizing a two-variable function on a square
par: Chervonenkis, Boris, et autres
Publié: (2024)

Online Learning-guided Learning Rate Adaptation via Gradient Alignment
par: Jiang, Ruichen, et autres
Publié: (2025)

Randomized algorithms and PAC bounds for inverse reinforcement learning in continuous spaces
par: Kamoutsi, Angeliki, et autres
Publié: (2024)

Stable Nonconvex-Nonconcave Training via Linear Interpolation
par: Pethick, Thomas, et autres
Publié: (2023)

A globalized inexact semismooth Newton method for strongly convex optimal control problems
par: Wachsmuth, Daniel
Publié: (2025)

Convergence analysis of inexact MBA method for constrained upper-$\mathcal{C}^2$ optimization problems
par: Liu, Ruyu, et autres
Publié: (2025)

SGD with memory: fundamental properties and stochastic acceleration
par: Yarotsky, Dmitry, et autres
Publié: (2024)