Online Optimization Perspective on First-Order and Zero-Order Decentralized Nonsmooth Nonconvex Stochastic Optimization

• URL: http://arxiv.org/abs/2406.01484v1
• Date: Mon, 3 Jun 2024 16:09:34 GMT
• Title: Online Optimization Perspective on First-Order and Zero-Order Decentralized Nonsmooth Nonconvex Stochastic Optimization
• Authors: Emre Sahinoglu, Shahin Shahrampour,
• Abstract summary: We investigate the finite-time analysis of finding ($delta,,ilon$)-stationary points for nonsmooth nonsmooth objectives in decentralized settings. $O is the first finite-time guarantee for decentralized nonsmooth optimization.
• Score: 8.670873561640903
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We investigate the finite-time analysis of finding ($\delta,\epsilon$)-stationary points for nonsmooth nonconvex objectives in decentralized stochastic optimization. A set of agents aim at minimizing a global function using only their local information by interacting over a network. We present a novel algorithm, called Multi Epoch Decentralized Online Learning (ME-DOL), for which we establish the sample complexity in various settings. First, using a recently proposed online-to-nonconvex technique, we show that our algorithm recovers the optimal convergence rate of smooth nonconvex objectives. We then extend our analysis to the nonsmooth setting, building on properties of randomized smoothing and Goldstein-subdifferential sets. We establish the sample complexity of $O(\delta^{-1}\epsilon^{-3})$, which to the best of our knowledge is the first finite-time guarantee for decentralized nonsmooth nonconvex stochastic optimization in the first-order setting (without weak-convexity), matching its optimal centralized counterpart. We further prove the same rate for the zero-order oracle setting without using variance reduction.

Related papers

• Stochastic Zeroth-Order Optimization under Strongly Convexity and Lipschitz Hessian: Minimax Sample Complexity [59.75300530380427]
  We consider the problem of optimizing second-order smooth and strongly convex functions where the algorithm is only accessible to noisy evaluations of the objective function it queries. We provide the first tight characterization for the rate of the minimax simple regret by developing matching upper and lower bounds.
  arXiv  Detail & Related papers  (2024-06-28T02:56:22Z)
• An Algorithm with Optimal Dimension-Dependence for Zero-Order Nonsmooth Nonconvex Stochastic Optimization [37.300102993926046]
  We study the complexity of producing neither smooth nor convex points of Lipschitz objectives which are possibly using only zero-order evaluations. Our analysis is based on a simple yet powerful. Goldstein-subdifferential set, which allows recent advancements in. nonsmooth non optimization.
  arXiv  Detail & Related papers  (2023-07-10T11:56:04Z)
• Can Decentralized Stochastic Minimax Optimization Algorithms Converge Linearly for Finite-Sum Nonconvex-Nonconcave Problems? [56.62372517641597]
  Decentralized minimax optimization has been actively studied in the past few years due to its application in a wide range machine learning. This paper develops two novel decentralized minimax optimization algorithms for the non-strongly-nonconcave problem.
  arXiv  Detail & Related papers  (2023-04-24T02:19:39Z)
• Near-Optimal Decentralized Momentum Method for Nonconvex-PL Minimax Problems [39.197569803430646]
  Minimax optimization plays an important role in many machine learning tasks such as adversarial networks (GANs) and adversarial training. Although recently a wide variety of optimization methods have been proposed to solve the minimax problems, most of them ignore the distributed setting.
  arXiv  Detail & Related papers  (2023-04-21T11:38:41Z)
• Optimal Stochastic Non-smooth Non-convex Optimization through Online-to-Non-convex Conversion [56.92236659731376]
  We present new algorithms for optimizing non-known, non-smooth objectives based on a novel analysis technique. For deterministic second-order smooth objectives, applying advanced optimistic online learning techniques enables a new $O(delta0.5) all$ to recover optimal or best-known results.
  arXiv  Detail & Related papers  (2023-02-07T22:09:20Z)
• Pick your Neighbor: Local Gauss-Southwell Rule for Fast Asynchronous Decentralized Optimization [37.85806148420504]
  In decentralized optimization environments, each agent $i$ in a network of $n$ optimization nodes possesses a private function $f_i$. We introduce an optimization-aware selection rule that chooses the neighbor with the highest dual cost improvement. We show that the proposed set-wise GS rule achieves a speedup by a factor of up to the maximum degree in the network.
  arXiv  Detail & Related papers  (2022-07-15T15:37:03Z)
• On Stochastic Moving-Average Estimators for Non-Convex Optimization [105.22760323075008]
  In this paper, we demonstrate the power of a widely used estimator based on moving average (SEMA) problems. For all these-the-art results, we also present the results for all these-the-art problems.
  arXiv  Detail & Related papers  (2021-04-30T08:50:24Z)
• A hybrid variance-reduced method for decentralized stochastic non-convex optimization [15.447966950703947]
  textttGTHSGD algorithm specialized local hybrid gradient implements the network to track the global gradient. textttGTHSGD achieves a network complexity of$O(n-1)$ when the required error tolerance$epsilon$ is small enough.
  arXiv  Detail & Related papers  (2021-02-12T20:13:05Z)
• Byzantine-Resilient Non-Convex Stochastic Gradient Descent [61.6382287971982]
  adversary-resilient distributed optimization, in which. machines can independently compute gradients, and cooperate. Our algorithm is based on a new concentration technique, and its sample complexity. It is very practical: it improves upon the performance of all prior methods when no. setting machines are present.
  arXiv  Detail & Related papers  (2020-12-28T17:19:32Z)
• Convergence of adaptive algorithms for weakly convex constrained optimization [59.36386973876765]
  We prove the $mathcaltilde O(t-1/4)$ rate of convergence for the norm of the gradient of Moreau envelope. Our analysis works with mini-batch size of $1$, constant first and second order moment parameters, and possibly smooth optimization domains.
  arXiv  Detail & Related papers  (2020-06-11T17:43:19Z)

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.