Cover Image

Double Variance Reduction: A Smoothing Trick for Composite Optimization Problems without First-Order Gradient

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Di, Hao, Ye, Haishan, Zhang, Yueling, Chang, Xiangyu, Dai, Guang, Tsang, Ivor W.
Format:	Preprint
Published:	2024
Subjects:	Machine Learning Optimization and Control
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Optimal Decentralized Composite Optimization for Convex Functions
by: Ye, Haishan, et al.
Published: (2023)

High-Probability Guarantees for Random Zeroth-Order Gradient Descent on Smooth Functions
by: Ye, Haishan
Published: (2026)

A Unified Zeroth-Order Optimization Framework via Oblivious Randomized Sketching
by: Ye, Haishan, et al.
Published: (2025)

Decentralized Riemannian Conjugate Gradient Method on the Stiefel Manifold
by: Chen, Jun, et al.
Published: (2023)

High-Probability Guarantees for Random Zeroth-Order (Stochastic) Gradient Descent
by: Ye, Haishan
Published: (2026)

Riemannian Momentum Tracking: Distributed Optimization with Momentum on Compact Submanifolds
by: Chen, Jun, et al.
Published: (2026)

Can a One-Point Feedback Zeroth-order Algorithm Achieve Linear Dimension Dependent Sample Complexity?
by: Ye, Haishan, et al.
Published: (2025)

ZIVR: An Incremental Variance Reduction Technique For Zeroth-Order Composite Problems
by: Zhang, Silan, et al.
Published: (2026)

Why Does Adaptive Zeroth-Order Optimization Work?
by: Ye, Haishan, et al.
Published: (2026)

Decentralized Optimization on Compact Submanifolds by Quantized Riemannian Gradient Tracking
by: Chen, Jun, et al.
Published: (2025)

Explicit and Non-asymptotic Query Complexities of Rank-Based Zeroth-order Algorithm on Stochastic Smooth Functions
by: Ye, Haishan
Published: (2025)

Stochastic Non-Smooth Non-Convex Optimization with Decision-Dependent Distributions
by: Liu, Chengchang, et al.
Published: (2026)

Anderson Acceleration Without Restart: A Novel Method with $n$-Step Super Quadratic Convergence Rate
by: Ye, Haishan, et al.
Published: (2024)

Shuffling Gradient Descent-Ascent with Variance Reduction for Nonconvex-Strongly Concave Smooth Minimax Problems
by: Jiang, Xia, et al.
Published: (2024)

Efficient First Order Method for Saddle Point Problems with Higher Order Smoothness
by: Wang, Nuozhou, et al.
Published: (2023)

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

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

Variance-Reduced Gradient Estimator for Nonconvex Zeroth-Order Distributed Optimization
by: Mu, Huaiyi, et al.
Published: (2024)

Variable Smoothing Alternating Proximal Gradient Algorithm for Coupled Composite Optimization
by: Long, Xian-Jun, et al.
Published: (2025)

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

Stochastic Gradient Langevin Dynamics with Variance Reduction
by: Huang, Zhishen, et al.
Published: (2021)

Gradient Estimation and Variance Reduction in Stochastic and Deterministic Models
by: Keane, Ronan
Published: (2024)

A First-Order Gradient Approach for the Connectivity Optimization of Markov Chains
by: Franssen, Christian P. C., et al.
Published: (2024)

Convex Synthesis of First-Order Methods for Time-Varying Smooth Strongly Convex Optimization
by: Van Scoy, Bryan, et al.
Published: (2026)

Doubly Smoothed Optimistic Gradients: A Universal Approach for Smooth Minimax Problems
by: Zheng, Taoli, et al.
Published: (2025)

First Order Algorithm on an Optimization Problem with Improved Convergence when Problem is Convex
by: Sim, Chee-Khian
Published: (2025)

On Solving Minimization and Min-Max Problems by First-Order Methods with Relative Error in Gradients
by: Vasin, Artem, et al.
Published: (2025)

Trust-Region Stochastic Optimization with Variance Reduction Technique
by: Zheng, Xinshou
Published: (2024)

Gradient Descent for Convex and Smooth Noisy Optimization
by: Hu, Feifei, et al.
Published: (2024)

First- and Second-Order Analysis for Optimization Problems with Manifold-Valued Constraints
by: Bergmann, Ronny, et al.
Published: (2021)

A Compositional Framework for First-Order Optimization
by: Hanks, Tyler, et al.
Published: (2024)

New Aspects of Black Box Conditional Gradient: Variance Reduction and One Point Feedback
by: Veprikov, Andrey, et al.
Published: (2024)

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

First-Order Methods for Nonsmooth Nonconvex Functional Constrained Optimization with or without Slater Points
by: Jia, Zhichao, et al.
Published: (2022)

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

Projection-Free Variance Reduction Methods for Stochastic Constrained Multi-Level Compositional Optimization
by: Jiang, Wei, et al.
Published: (2024)

First-Order Algorithms Without Lipschitz Gradient: A Sequential Local Optimization Approach
by: Zhang, Junyu, et al.
Published: (2020)

On Constraints in First-Order Optimization: A View from Non-Smooth Dynamical Systems
by: Muehlebach, Michael, et al.
Published: (2021)

An Efficient Stochastic Algorithm for Decentralized Nonconvex-Strongly-Concave Minimax Optimization
by: Chen, Lesi, et al.
Published: (2022)

Adaptive Accelerated Gradient Method for Smooth Convex Optimization
by: Wang, Zepeng, et al.
Published: (2025)