Cover Image

Second-order Information Promotes Mini-Batch Robustness in Variance-Reduced Gradients

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Garg, Sachin, Berahas, Albert S., Dereziński, Michał
Format:	Preprint
Published:	2024
Subjects:	Optimization and Control Machine Learning 65K05, 90C06, 90C30
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Retrospective Approximation Sequential Quadratic Programming for Stochastic Optimization with General Deterministic Nonlinear Constraints
by: Berahas, Albert S., et al.
Published: (2025)

Variational Properties of Decomposable Functions. Part II: Strong Second-Order Theory
by: Ouyang, Wenqing, et al.
Published: (2023)

Gradient descent with adaptive stepsize converges (nearly) linearly under fourth-order growth
by: Davis, Damek, et al.
Published: (2024)

A MINRES-based Linesearch Algorithm for Nonconvex Optimization with Non-positive Curvature Detection
by: Zeng, Hanfeng, et al.
Published: (2026)

Accelerated Gradient Methods with Gradient Restart: Global Linear Convergence
by: Bao, Chenglong, et al.
Published: (2024)

A linesearch-type normal map-based semismooth Newton method for nonsmooth nonconvex composite optimization
by: Zeng, Hanfeng, et al.
Published: (2026)

Mixed-integer linearity in nonlinear optimization: a trust region approach
by: De Marchi, Alberto
Published: (2023)

Variational Properties of Decomposable Functions. Part I: Strict Epi-Calculus and Applications
by: Ouyang, Wenqing, et al.
Published: (2023)

A Lasry-Lions envelope approach for mathematical programs with complementarity constraints
by: Wang, Jia, et al.
Published: (2025)

Randomized block proximal method with locally Lipschitz continuous gradient
by: Pérez-Aros, Pedro, et al.
Published: (2025)

On the convergence of proximal gradient methods for convex simple bilevel optimization
by: Latafat, Puya, et al.
Published: (2023)

Hybrid optimal control with mixed-integer Lagrangian methods
by: Nikitina, Viktoriya, et al.
Published: (2024)

Affordable mixed-integer Lagrangian methods: optimality conditions and convergence analysis
by: De Marchi, Alberto
Published: (2024)

The Global R-linear Convergence of Nesterov's Accelerated Gradient Method with Unknown Strongly Convex Parameter
by: Bao, Chenglong, et al.
Published: (2023)

A non-monotone trust-region method with noisy oracles and additional sampling
by: Krejic, Natasa, et al.
Published: (2023)

Oracle complexities of augmented Lagrangian methods for nonsmooth manifold optimization
by: Deng, Kangkang, et al.
Published: (2024)

Bregman Stochastic Proximal Point Algorithm with Variance Reduction
by: Traoré, Cheik, et al.
Published: (2025)

Inexact Riemannian Gradient Descent Method for Nonconvex Optimization
by: Zhou, Juan, et al.
Published: (2024)

Fast Frank--Wolfe Algorithms with Adaptive Bregman Step-Size for Weakly Convex Functions
by: Takahashi, Shota, et al.
Published: (2025)

On the convergence of adaptive first order methods: proximal gradient and alternating minimization algorithms
by: Latafat, Puya, et al.
Published: (2023)

A globalization of L-BFGS and the Barzilai-Borwein method for nonconvex unconstrained optimization
by: Mannel, Florian
Published: (2024)

Heavy-ball Differential Equation Achieves $O(\varepsilon^{-7/4})$ Convergence for Nonconvex Functions
by: Okamura, Kaito, et al.
Published: (2024)

Stability and convergence analysis of AdaGrad for non-convex optimization via novel stopping time-based techniques
by: Jin, Ruinan, et al.
Published: (2024)

Asymptotic Convergence and Stability of Adaptive Gradient Methods in Smooth Non-convex Optimization
by: Jin, Ruinan, et al.
Published: (2026)

On the Convergence and Complexity of Proximal Gradient and Accelerated Proximal Gradient Methods under Adaptive Gradient Estimation
by: Bollapragada, Raghu, et al.
Published: (2025)

Preconditioned Proximal Gradient Methods with Conjugate Momentum: A Subspace Perspective
by: Chen, Jian, et al.
Published: (2026)

Proximal Gradient Descent Ascent Methods for Nonsmooth Nonconvex-Concave Minimax Problems on Riemannian Manifolds
by: Xie, Xiyuan, et al.
Published: (2025)

A structured L-BFGS method and its application to inverse problems
by: Mannel, Florian, et al.
Published: (2023)

A structured L-BFGS method with diagonal scaling and its application to image registration
by: Mannel, Florian, et al.
Published: (2024)

On the asymptotic behavior of a higher-order extrapolation primal-dual interior-point method for nonlinear programming
by: Heeman, Pim, et al.
Published: (2025)

Adaptive proximal gradient methods are universal without approximation
by: Oikonomidis, Konstantinos A., et al.
Published: (2024)

Adaptive proximal algorithms for convex optimization under local Lipschitz continuity of the gradient
by: Latafat, Puya, et al.
Published: (2023)

Safeguarding adaptive methods: global convergence of Barzilai-Borwein and other stepsize choices
by: Ou, Hongjia, et al.
Published: (2024)

Linesearch-free adaptive Bregman proximal gradient for convex minimization without relative smoothness
by: Ou, Hongjia, et al.
Published: (2025)

Line-search and Adaptive Step Sizes for Nonconvex-strongly-concave Minimax Optimization
by: Ma, Bohao, et al.
Published: (2026)

Simplex Frank-Wolfe: Linear Convergence and Its Numerical Efficiency for Convex Optimization over Polytopes
by: Wang, Haoning, et al.
Published: (2025)

$Q$-fully Quadratic Modeling and its Application in a Random Subspace Derivative-free Method
by: Chen, Yiwen, et al.
Published: (2023)

On a globally convergent semismooth* Newton method in nonsmooth nonconvex optimization
by: Gfrerer, H.
Published: (2024)

CLARSTA: A random subspace trust-region algorithm for convex-constrained derivative-free optimization
by: Chen, Yiwen, et al.
Published: (2025)

Anderson Accelerated Primal-Dual Hybrid Gradient for solving LP
by: Zhou, Yingxin, et al.
Published: (2025)