An Efficient Stochastic Algorithm for Decentralized Nonconvex-Strongly-Concave Minimax Optimization
- URL: http://arxiv.org/abs/2212.02387v4
- Date: Tue, 14 May 2024 10:41:02 GMT
- Title: An Efficient Stochastic Algorithm for Decentralized Nonconvex-Strongly-Concave Minimax Optimization
- Authors: Lesi Chen, Haishan Ye, Luo Luo,
- Abstract summary: Decentralized Recursive desc. Method (DREAM)
Concretely, it requires $mathcalO(minminappaappa3eps-3,kappa2 N)$ first-order oracle (SFO) calls and $tildemathcalO(kappa2 epsilon-2) communication rounds.
Our numerical experiments validate the superiority of previous methods.
- Score: 25.00475462213752
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: 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 theoretical guarantee for finding the $\epsilon$-stationary points. Concretely, it requires $\mathcal{O}(\min (\kappa^3\epsilon^{-3},\kappa^2 \sqrt{N} \epsilon^{-2} ))$ stochastic first-order oracle (SFO) calls and $\tilde{\mathcal{O}}(\kappa^2 \epsilon^{-2})$ communication rounds, where $\kappa$ is the condition number and $N$ is the total number of individual functions. Our numerical experiments also validate the superiority of DREAM over previous methods.
Related papers
- Quantum Algorithms for Non-smooth Non-convex Optimization [30.576546266390714]
This paper considers the problem for finding the $(,epsilon)$-Goldstein stationary point of Lipschitz continuous objective.
We construct a zeroth-order quantum estimator for the surrogate oracle function.
arXiv Detail & Related papers (2024-10-21T16:52:26Z) - Projection-Free Methods for Stochastic Simple Bilevel Optimization with
Convex Lower-level Problem [16.9187409976238]
We study a class of convex bilevel optimization problems, also known as simple bilevel optimization.
We introduce novel bilevel optimization methods that approximate the solution set of the lower-level problem.
arXiv Detail & Related papers (2023-08-15T02:37:11Z) - Accelerating Inexact HyperGradient Descent for Bilevel Optimization [84.00488779515206]
We present a method for solving general non-strongly-concave bilevel optimization problems.
Our results also improve upon the existing complexity for finding second-order stationary points in non-strongly-concave problems.
arXiv Detail & Related papers (2023-06-30T20:36:44Z) - ReSQueing Parallel and Private Stochastic Convex Optimization [59.53297063174519]
We introduce a new tool for BFG convex optimization (SCO): a Reweighted Query (ReSQue) estimator for the gradient of a function convolved with a (Gaussian) probability density.
We develop algorithms achieving state-of-the-art complexities for SCO in parallel and private settings.
arXiv Detail & Related papers (2023-01-01T18:51:29Z) - An Optimal Stochastic Algorithm for Decentralized Nonconvex Finite-sum
Optimization [25.21457349137344]
We show a proof to show DEAREST requires at most $mathcal O(+sqrtmnLvarepsilon-2)$ first-order oracle (IFO) calls and $mathcal O(Lvarepsilon-2/sqrt1-lambda_W)$ communication rounds.
arXiv Detail & Related papers (2022-10-25T11:37:11Z) - Decentralized Stochastic Variance Reduced Extragradient Method [25.21457349137344]
This paper studies decentralized convex-concave minimax optimization problems of the form $min_xmax_y fx,y triqfrac1msumi=1m f_i triqfrac1msumi=1m f_i triqfrac1msumi=1m f_i triqfrac1msumi=1m f_i triqfrac1msum
arXiv Detail & Related papers (2022-02-01T16:06:20Z) - Bayesian Optimistic Optimisation with Exponentially Decaying Regret [58.02542541410322]
The current practical BO algorithms have regret bounds ranging from $mathcalO(fraclogNsqrtN)$ to $mathcal O(e-sqrtN)$, where $N$ is the number of evaluations.
This paper explores the possibility of improving the regret bound in the noiseless setting by intertwining concepts from BO and tree-based optimistic optimisation.
We propose the BOO algorithm, a first practical approach which can achieve an exponential regret bound with order $mathcal O(N-sqrt
arXiv Detail & Related papers (2021-05-10T13:07:44Z) - A Momentum-Assisted Single-Timescale Stochastic Approximation Algorithm
for Bilevel Optimization [112.59170319105971]
We propose a new algorithm -- the Momentum- Single-timescale Approximation (MSTSA) -- for tackling problems.
MSTSA allows us to control the error in iterations due to inaccurate solution to the lower level subproblem.
arXiv Detail & Related papers (2021-02-15T07:10:33Z) - Accelerated Zeroth-Order and First-Order Momentum Methods from Mini to
Minimax Optimization [133.53164856723782]
We propose a new accelerated zeroth-order momentum (AccZOM) method for black-box mini-optimization where only function values can be obtained.
Meanwhile, we propose an accelerated zeroth-order momentum descent (Acc-MDA) method for black-box minimax optimization, where only function values can be obtained.
In particular, our Acc-MDA can obtain a lower gradient complexity of $tildeO(kappa_y2.5epsilon-3)$ with a batch size $O(kappa_y4)$.
arXiv Detail & Related papers (2020-08-18T22:19:29Z) - Second-Order Information in Non-Convex Stochastic Optimization: Power
and Limitations [54.42518331209581]
We find an algorithm which finds.
epsilon$-approximate stationary point (with $|nabla F(x)|le epsilon$) using.
$(epsilon,gamma)$surimate random random points.
Our lower bounds here are novel even in the noiseless case.
arXiv Detail & Related papers (2020-06-24T04:41:43Z) - Stochastic Recursive Gradient Descent Ascent for Stochastic
Nonconvex-Strongly-Concave Minimax Problems [36.645753881826955]
In this paper, we propose a novel method called RecurEnti Ascent (SREDA), which estimates more efficiently using variance.
This method achieves the best known for this problem.
arXiv Detail & Related papers (2020-01-11T09:05:03Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.