paper-with-me

Papers

Fully First-Order Methods for Decentralized Bilevel Optimization

2024-10-25 · Xiaoyu Wang, Xuxing Chen, Shiqian Ma, Tong Zhang

This paper focuses on decentralized stochastic bilevel optimization (DSBO) where agents only communicate with their neighbors. We propose Decentralized Stochastic Gradient Descent and Ascent with Gradient Tracking (DSGDA-GT), a novel algorithm that only requires first-order oracles that are much cheaper than second-order oracles widely adopted in existing works. We further provide a finite-time convergence analysis showing that for $n$ agents collaboratively solving the DSBO problem, the sample complexity of finding an $\epsilon$-stationary point in our algorithm is $\mathcal{O}(n^{-1}\epsilon^{-7})$, which matches the currently best-known results of the single-agent counterpart with linear speedup. The numerical experiments demonstrate both the communication and training efficiency of our algorithm.

📄 PDF Abstract BibTeX arXiv:2410.19319

Code (0)

등록된 구현이 없습니다.

Tasks

Bilevel Optimization

Similar Papers 제목 키워드 기반

A Communication and Computation Efficient Fully First-order Method for Decentralized Bilevel Optimization

2024-10-18 · Min Wen, Chengchang Liu, Ahmed Abdelmoniem, Yipeng Zhou 외

Bilevel optimization, crucial for hyperparameter tuning, meta-learning and reinforcement learning, remains less explored in the decentralized learning paradigm, such as decentralized federated learning (DFL). Typically, …

Bilevel OptimizationFederated LearningMeta-Learning

Decentralized Bilevel Optimization: A Perspective from Transient Iteration Complexity

2024-02-05 · Boao Kong, Shuchen Zhu, Songtao Lu, Xinmeng Huang 외

Stochastic bilevel optimization (SBO) is becoming increasingly essential in machine learning due to its versatility in handling nested structures. To address large-scale SBO, decentralized approaches have emerged as effe…

Bilevel Optimization

A Single-Loop Algorithm for Decentralized Bilevel Optimization

2023-11-15 · Youran Dong, Shiqian Ma, Junfeng Yang, Chao Yin

Bilevel optimization has gained significant attention in recent years due to its broad applications in machine learning. This paper focuses on bilevel optimization in decentralized networks and proposes a novel single-lo…

Bilevel OptimizationHyperparameter Optimization

Decentralized Stochastic Bilevel Optimization with Improved per-Iteration Complexity

2022-10-23 · Xuxing Chen, Minhui Huang, Shiqian Ma, Krishnakumar Balasubramanian

Bilevel optimization recently has received tremendous attention due to its great success in solving important machine learning problems like meta learning, reinforcement learning, and hyperparameter optimization. Extendi…

Bilevel OptimizationHyperparameter OptimizationMeta-LearningStochastic Optimization

Nonconvex Decentralized Stochastic Bilevel Optimization under Heavy-Tailed Noise

2025-09-19 · Xinwen Zhang, Yihan Zhang, Heng Liang, Hongchang Gao arxiv

Existing decentralized stochastic optimization methods assume the lower-level loss function is strongly convex and the stochastic gradient noise has finite variance. These strong assumptions typically are not satisfied i…

Stochastic OptimizationBilevel Optimization