Zobrazeno 1 - 10
of 21
pro vyhledávání: '"Chen, Lesi"'
This paper studies second-order methods for convex-concave minimax optimization. Monteiro and Svaiter (2012) proposed a method to solve the problem with an optimal iteration complexity of $\mathcal{O}(\epsilon^{-3/2})$ to find an $\epsilon$-saddle po
Externí odkaz:
http://arxiv.org/abs/2410.09568
This paper studies simple bilevel problems, where a convex upper-level function is minimized over the optimal solutions of a convex lower-level problem. We first show the fundamental difficulty of simple bilevel problems, that the approximate optimal
Externí odkaz:
http://arxiv.org/abs/2409.06530
This paper considers stochastic first-order algorithms for minimax optimization under Polyak--{\L}ojasiewicz (PL) conditions. We propose SPIDER-GDA for solving the finite-sum problem of the form $\min_x \max_y f(x,y)\triangleq \frac{1}{n} \sum_{i=1}^
Externí odkaz:
http://arxiv.org/abs/2307.15868
Bilevel optimization has wide applications such as hyperparameter tuning, neural architecture search, and meta-learning. Designing efficient algorithms for bilevel optimization is challenging because the lower-level problem defines a feasibility set
Externí odkaz:
http://arxiv.org/abs/2306.14853
We propose a communication and computation efficient second-order method for distributed optimization. For each iteration, our method only requires $\mathcal{O}(d)$ communication complexity, where $d$ is the problem dimension. We also provide theoret
Externí odkaz:
http://arxiv.org/abs/2305.17945
We consider the optimization problem of the form $\min_{x \in \mathbb{R}^d} f(x) \triangleq \mathbb{E}_{\xi} [F(x; \xi)]$, where the component $F(x;\xi)$ is $L$-mean-squared Lipschitz but possibly nonconvex and nonsmooth. The recently proposed gradie
Externí odkaz:
http://arxiv.org/abs/2301.06428
Bilevel optimization reveals the inner structure of otherwise oblique optimization problems, such as hyperparameter tuning, neural architecture search, and meta-learning. A common goal in bilevel optimization is to minimize a hyper-objective that imp
Externí odkaz:
http://arxiv.org/abs/2301.00712
This paper studies the stochastic nonconvex-strongly-concave minimax optimization over a multi-agent network. We propose an efficient algorithm, called Decentralized Recursive gradient descEnt Ascent Method (DREAM), which achieves the best-known theo
Externí odkaz:
http://arxiv.org/abs/2212.02387
Autor:
Chen, Lesi, Luo, Luo
We study the problem of finding a near-stationary point for smooth minimax optimization. The recent proposed extra anchored gradient (EAG) methods achieve the optimal convergence rate for the convex-concave minimax problem in deterministic setting. H
Externí odkaz:
http://arxiv.org/abs/2208.05925
Bilevel optimization has various applications such as hyper-parameter optimization and meta-learning. Designing theoretically efficient algorithms for bilevel optimization is more challenging than standard optimization because the lower-level problem
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::40d1fa157da58b880b327a51e4d0c0dd