Proving the Limited Scalability of Centralized Distributed Optimization via a New Lower Bound Construction

• URL: http://arxiv.org/abs/2506.23836v1
• Date: Mon, 30 Jun 2025 13:27:39 GMT
• Title: Proving the Limited Scalability of Centralized Distributed Optimization via a New Lower Bound Construction
• Authors: Alexander Tyurin,
• Abstract summary: We consider a centralized distributed learning setup where all workers jointly find an unbiased bound LDeltaepsilon2,$ better poly-logarithmically in $n$, even in the homogeneous (i.i.d.) case, where all workers access the same distribution.
• Score: 57.93371273485736
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We consider centralized distributed optimization in the classical federated learning setup, where $n$ workers jointly find an $\varepsilon$-stationary point of an $L$-smooth, $d$-dimensional nonconvex function $f$, having access only to unbiased stochastic gradients with variance $\sigma^2$. Each worker requires at most $h$ seconds to compute a stochastic gradient, and the communication times from the server to the workers and from the workers to the server are $\tau_{s}$ and $\tau_{w}$ seconds per coordinate, respectively. One of the main motivations for distributed optimization is to achieve scalability with respect to $n$. For instance, it is well known that the distributed version of SGD has a variance-dependent runtime term $\frac{h \sigma^2 L \Delta}{n \varepsilon^2},$ which improves with the number of workers $n,$ where $\Delta = f(x^0) - f^*,$ and $x^0 \in R^d$ is the starting point. Similarly, using unbiased sparsification compressors, it is possible to reduce both the variance-dependent runtime term and the communication runtime term. However, once we account for the communication from the server to the workers $\tau_{s}$, we prove that it becomes infeasible to design a method using unbiased random sparsification compressors that scales both the server-side communication runtime term $\tau_{s} d \frac{L \Delta}{\varepsilon}$ and the variance-dependent runtime term $\frac{h \sigma^2 L \Delta}{\varepsilon^2},$ better than poly-logarithmically in $n$, even in the homogeneous (i.i.d.) case, where all workers access the same distribution. To establish this result, we construct a new "worst-case" function and develop a new lower bound framework that reduces the analysis to the concentration of a random sum, for which we prove a concentration bound. These results reveal fundamental limitations in scaling distributed optimization, even under the homogeneous assumption.

Related papers

• Robust Distribution Learning with Local and Global Adversarial Corruptions [17.22168727622332]
  We develop an efficient finite-sample algorithm with error bounded by $sqrtvarepsilon k + rho + tildeO(dsqrtkn-1/(k lor 2))$ when $P$ has bounded covariance. Our efficient procedure relies on a novel trace norm approximation of an ideal yet intractable 2-Wasserstein projection estimator.
  arXiv  Detail & Related papers  (2024-06-10T17:48:36Z)
• Policy Gradient Optimal Correlation Search for Variance Reduction in Monte Carlo simulation and Maximum Optimal Transport [0.0]
  We propose a new algorithm for variance reduction when estimating $f(X_T)$ where $X$ is the solution to some differential equation and $f$ is a test function. The new estimator is $(f(XT) + f(X2_T))/2$, where $X1$ and $X2$ have same marginal law as $X2$ but are pathwise correlated so that to reduce the variance.
  arXiv  Detail & Related papers  (2023-07-24T11:37:02Z)
• An Oblivious Stochastic Composite Optimization Algorithm for Eigenvalue Optimization Problems [76.2042837251496]
  We introduce two oblivious mirror descent algorithms based on a complementary composite setting. Remarkably, both algorithms work without prior knowledge of the Lipschitz constant or smoothness of the objective function. We show how to extend our framework to scale and demonstrate the efficiency and robustness of our methods on large scale semidefinite programs.
  arXiv  Detail & Related papers  (2023-06-30T08:34:29Z)
• Stochastic Approximation Approaches to Group Distributionally Robust Optimization and Beyond [89.72693227960274]
  This paper investigates group distributionally robust optimization (GDRO) with the goal of learning a model that performs well over $m$ different distributions. To reduce the number of samples in each round from $m$ to 1, we cast GDRO as a two-player game, where one player conducts and the other executes an online algorithm for non-oblivious multi-armed bandits. In the second scenario, we propose to optimize the average top-$k$ risk instead of the maximum risk, thereby mitigating the impact of distributions.
  arXiv  Detail & Related papers  (2023-02-18T09:24:15Z)
• DADAO: Decoupled Accelerated Decentralized Asynchronous Optimization [0.0]
  DADAO is the first decentralized, accelerated, asynchronous, primal, first-order algorithm to minimize a sum of $L$-smooth and $mu$-strongly convex functions distributed over a given network of size $n$. We show that our algorithm requires $mathcalO(nsqrtchisqrtfracLmulog(frac1epsilon)$ local and only $mathcalO(nsqrtchisqrtfracLmulog(
  arXiv  Detail & Related papers  (2022-07-26T08:47:54Z)
• Sharper Convergence Guarantees for Asynchronous SGD for Distributed and Federated Learning [77.22019100456595]
  We show a training algorithm for distributed computation workers with varying communication frequency. In this work, we obtain a tighter convergence rate of $mathcalO!!!(sigma2-2_avg!! . We also show that the heterogeneity term in rate is affected by the average delay within each worker.
  arXiv  Detail & Related papers  (2022-06-16T17:10:57Z)
• Optimal Gradient Sliding and its Application to Distributed Optimization Under Similarity [121.83085611327654]
  We structured convex optimization problems with additive objective $r:=p + q$, where $r$ is $mu$-strong convex similarity. We proposed a method to solve problems master to agents' communication and local calls. The proposed method is much sharper than the $mathcalO(sqrtL_q/mu)$ method.
  arXiv  Detail & Related papers  (2022-05-30T14:28:02Z)
• TURF: A Two-factor, Universal, Robust, Fast Distribution Learning Algorithm [64.13217062232874]
  One of its most powerful and successful modalities approximates every distribution to an $ell$ distance essentially at most a constant times larger than its closest $t$-piece degree-$d_$. We provide a method that estimates this number near-optimally, hence helps approach the best possible approximation.
  arXiv  Detail & Related papers  (2022-02-15T03:49:28Z)
• Sampling from Log-Concave Distributions with Infinity-Distance Guarantees and Applications to Differentially Private Optimization [33.38289436686841]
  We present an algorithm that outputs a point from a distributionO(varepsilon)$close to $$ in infinity-distance. We also present a "soft-pi" version of the Dikin walk which may be independent interest.
  arXiv  Detail & Related papers  (2021-11-07T13:44:50Z)
• Asynchronous Stochastic Optimization Robust to Arbitrary Delays [54.61797739710608]
  We consider optimization with delayed gradients where, at each time stept$, the algorithm makes an update using a stale computation - d_t$ for arbitrary delay $d_t gradient. Our experiments demonstrate the efficacy and robustness of our algorithm in cases where the delay distribution is skewed or heavy-tailed.
  arXiv  Detail & Related papers  (2021-06-22T15:50:45Z)

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.