Distributed Online Convex Optimization with Efficient Communication: Improved Algorithm and Lower bounds

• URL: http://arxiv.org/abs/2601.04907v2
• Date: Fri, 09 Jan 2026 03:05:42 GMT
• Title: Distributed Online Convex Optimization with Efficient Communication: Improved Algorithm and Lower bounds
• Authors: Sifan Yang, Wenhao Yang, Wei Jiang, Lijun Zhang,
• Abstract summary: We investigate distributed online convex optimization with compressed communication.<n>We propose a novel algorithm that achieves improved regret bounds of $tildeO(-1/2-1nsqrtT)$ and $tildeO(-1-2nlnT)$ for convex and strongly convex functions.
• Score: 27.851263935083736
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We investigate distributed online convex optimization with compressed communication, where $n$ learners connected by a network collaboratively minimize a sequence of global loss functions using only local information and compressed data from neighbors. Prior work has established regret bounds of $O(\max\{ω^{-2}ρ^{-4}n^{1/2},ω^{-4}ρ^{-8}\}n\sqrt{T})$ and $O(\max\{ω^{-2}ρ^{-4}n^{1/2},ω^{-4}ρ^{-8}\}n\ln{T})$ for convex and strongly convex functions, respectively, where $ω\in(0,1]$ is the compression quality factor ($ω=1$ means no compression) and $ρ<1$ is the spectral gap of the communication matrix. However, these regret bounds suffer from a quadratic or even quartic dependence on $ω^{-1}$. Moreover, the super-linear dependence on $n$ is also undesirable. To overcome these limitations, we propose a novel algorithm that achieves improved regret bounds of $\tilde{O}(ω^{-1/2}ρ^{-1}n\sqrt{T})$ and $\tilde{O}(ω^{-1}ρ^{-2}n\ln{T})$ for convex and strongly convex functions, respectively. The primary idea is to design a two-level blocking update framework incorporating two novel ingredients: an online gossip strategy and an error compensation scheme, which collaborate to achieve a better consensus among learners. Furthermore, we establish the first lower bounds for this problem, justifying the optimality of our results with respect to both $ω$ and $T$. Additionally, we consider the bandit feedback scenario, and extend our method with the classic gradient estimators to enhance existing regret bounds.

Related papers

• On the Condition Number Dependency in Bilevel Optimization [23.985835962136793]
  Bilevel optimization between an objective function defined by an upper-level problem whose feasible region is the solution of a lower-level problem.<n>For second-order and hyper-smooth problems, we show $(_y13/4 )$ and $(4-4)$ respectively.
  arXiv  Detail & Related papers  (2025-11-27T11:03:24Z)
• Adaptivity and Universality: Problem-dependent Universal Regret for Online Convex Optimization [64.88607416000376]
  We introduce UniGrad, a novel approach that achieves both universality and adaptivity, with two distinct realizations: UniGrad.Correct and UniGrad.Bregman.<n>Both methods achieve universal regret guarantees that adapt to gradient variation, simultaneously attaining $mathcalO(log V_T)$ regret for strongly convex functions and $mathcalO(d log V_T)$ regret for exp-concave functions.
  arXiv  Detail & Related papers  (2025-11-25T05:23:10Z)
• Power Homotopy for Zeroth-Order Non-Convex Optimizations [5.737648067191245]
  GS-Power is a novel zeroth-order method for non-dimensional optimization problems.<n>It consistently ranks among the top three across a suite of competing algorithms.<n>It achieved first place at least-likely targeted black-box attacks against images from ImageNet.
  arXiv  Detail & Related papers  (2025-11-17T16:54:30Z)
• Two-Timescale Gradient Descent Ascent Algorithms for Nonconvex Minimax Optimization [77.3396841985172]
  We provide a unified analysis of two-timescale gradient ascent (TTGDA) for solving structured non minimax optimization problems.<n>Our contribution is to design TTGDA algorithms are effective beyond the setting.
  arXiv  Detail & Related papers  (2024-08-21T20:14:54Z)
• Online Newton Method for Bandit Convex Optimisation [28.66596225688161]
  We introduce a computationally efficient algorithm for zeroth-order bandit convex optimisation. We prove that in the adversarial setting its regret is at most $d3.5 sqrtn mathrmpolylog(n, d)$ with high probability where $d$ is the time horizon. In the setting the bound improves to $M d2 sqrtn mathrmpolylog(n, d)$ where $M in [d-1/2, d-1 / 4]$ is
  arXiv  Detail & Related papers  (2024-06-10T17:44:11Z)
• Optimal and Efficient Algorithms for Decentralized Online Convex Optimization [51.00357162913229]
  Decentralized online convex optimization (D-OCO) is designed to minimize a sequence of global loss functions using only local computations and communications.<n>We develop a novel D-OCO algorithm that can reduce the regret bounds for convex and strongly convex functions to $tildeO(nrho-1/4sqrtT)$ and $tildeO(nrho-1/2log T)$.<n>Our analysis reveals that the projection-free variant can achieve $O(nT3/4)$ and $O(n
  arXiv  Detail & Related papers  (2024-02-14T13:44:16Z)
• Tackling Heavy-Tailed Rewards in Reinforcement Learning with Function Approximation: Minimax Optimal and Instance-Dependent Regret Bounds [26.277745106128197]
  In this work, we address the challenge of such rewards in reinforcement learning with linear function approximation. We first design an algorithm, textscHeavy-OFUL, for heavy-tailed linear bandits, achieving an emphinstance-dependent $T$-round regret of $tildeObig. Our result is achieved via a novel self-normalized concentration inequality that may be of independent interest in handling heavytailed noise in general online regression problems.
  arXiv  Detail & Related papers  (2023-06-12T02:56:09Z)
• Towards Painless Policy Optimization for Constrained MDPs [46.12526917024248]
  We study policy optimization in an infinite horizon, $gamma$-discounted constrained Markov decision process (CMDP) Our objective is to return a policy that achieves large expected reward with a small constraint violation. We propose a generic primal-dual framework that allows us to bound the reward sub-optimality and constraint violation for arbitrary algorithms.
  arXiv  Detail & Related papers  (2022-04-11T15:08:09Z)
• Private Stochastic Convex Optimization: Optimal Rates in $\ell_1$ Geometry [69.24618367447101]
  Up to logarithmic factors the optimal excess population loss of any $(varepsilon,delta)$-differently private is $sqrtlog(d)/n + sqrtd/varepsilon n.$ We show that when the loss functions satisfy additional smoothness assumptions, the excess loss is upper bounded (up to logarithmic factors) by $sqrtlog(d)/n + (log(d)/varepsilon n)2/3.
  arXiv  Detail & Related papers  (2021-03-02T06:53:44Z)
• Optimal Regret Algorithm for Pseudo-1d Bandit Convex Optimization [51.23789922123412]
  We study online learning with bandit feedback (i.e. learner has access to only zeroth-order oracle) where cost/reward functions admit a "pseudo-1d" structure. We show a lower bound of $min(sqrtdT, T3/4)$ for the regret of any algorithm, where $T$ is the number of rounds. We propose a new algorithm sbcalg that combines randomized online gradient descent with a kernelized exponential weights method to exploit the pseudo-1d structure effectively.
  arXiv  Detail & Related papers  (2021-02-15T08:16:51Z)
• Near-Optimal Regret Bounds for Contextual Combinatorial Semi-Bandits with Linear Payoff Functions [53.77572276969548]
  We show that the C$2$UCB algorithm has the optimal regret bound $tildeO(dsqrtkT + dk)$ for the partition matroid constraints. For general constraints, we propose an algorithm that modifies the reward estimates of arms in the C$2$UCB algorithm.
  arXiv  Detail & Related papers  (2021-01-20T04:29:18Z)
• Curse of Dimensionality on Randomized Smoothing for Certifiable Robustness [151.67113334248464]
  We show that extending the smoothing technique to defend against other attack models can be challenging. We present experimental results on CIFAR to validate our theory.
  arXiv  Detail & Related papers  (2020-02-08T22:02:14Z)

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.