A New Theoretical Perspective on Data Heterogeneity in Federated Optimization

• URL: http://arxiv.org/abs/2407.15567v1
• Date: Mon, 22 Jul 2024 11:52:58 GMT
• Title: A New Theoretical Perspective on Data Heterogeneity in Federated Optimization
• Authors: Jiayi Wang, Shiqiang Wang, Rong-Rong Chen, Mingyue Ji,
• Abstract summary: In federated learning (FL), data heterogeneity is the main reason that existing theoretical analyses are pessimistic about the convergence rate. In particular, for many FL algorithms, the convergence rate grows dramatically when the number of local updates becomes large. This paper aims to bridge this gap between theoretical understanding and practical performance by providing a theoretical analysis from a new perspective.
• Score: 39.75009345804017
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In federated learning (FL), data heterogeneity is the main reason that existing theoretical analyses are pessimistic about the convergence rate. In particular, for many FL algorithms, the convergence rate grows dramatically when the number of local updates becomes large, especially when the product of the gradient divergence and local Lipschitz constant is large. However, empirical studies can show that more local updates can improve the convergence rate even when these two parameters are large, which is inconsistent with the theoretical findings. This paper aims to bridge this gap between theoretical understanding and practical performance by providing a theoretical analysis from a new perspective on data heterogeneity. In particular, we propose a new and weaker assumption compared to the local Lipschitz gradient assumption, named the heterogeneity-driven pseudo-Lipschitz assumption. We show that this and the gradient divergence assumptions can jointly characterize the effect of data heterogeneity. By deriving a convergence upper bound for FedAvg and its extensions, we show that, compared to the existing works, local Lipschitz constant is replaced by the much smaller heterogeneity-driven pseudo-Lipschitz constant and the corresponding convergence upper bound can be significantly reduced for the same number of local updates, although its order stays the same. In addition, when the local objective function is quadratic, more insights on the impact of data heterogeneity can be obtained using the heterogeneity-driven pseudo-Lipschitz constant. For example, we can identify a region where FedAvg can outperform mini-batch SGD even when the gradient divergence can be arbitrarily large. Our findings are validated using experiments.

Related papers

• Generalization error of min-norm interpolators in transfer learning [2.7309692684728617]
  Min-norm interpolators emerge naturally as implicit regularized limits of modern machine learning algorithms. In many applications, a limited amount of test data may be available during training, yet properties of min-norm in this setting are not well-understood. We establish a novel anisotropic local law to achieve these characterizations.
  arXiv  Detail & Related papers  (2024-06-20T02:23:28Z)
• Nonparametric logistic regression with deep learning [1.2509746979383698]
  In the nonparametric logistic regression, the Kullback-Leibler divergence could diverge easily. Instead of analyzing the excess risk itself, it suffices to show the consistency of the maximum likelihood estimator. As an important application, we derive the convergence rates of the NPMLE with deep neural networks.
  arXiv  Detail & Related papers  (2024-01-23T04:31:49Z)
• Instance-Dependent Generalization Bounds via Optimal Transport [51.71650746285469]
  Existing generalization bounds fail to explain crucial factors that drive the generalization of modern neural networks. We derive instance-dependent generalization bounds that depend on the local Lipschitz regularity of the learned prediction function in the data space. We empirically analyze our generalization bounds for neural networks, showing that the bound values are meaningful and capture the effect of popular regularization methods during training.
  arXiv  Detail & Related papers  (2022-11-02T16:39:42Z)
• On the Unreasonable Effectiveness of Federated Averaging with Heterogeneous Data [39.600069116159695]
  Existing theory predicts that data heterogeneity will degrade the performance of the Federated Averaging (FedAvg) algorithm in federated learning. This paper explains the seemingly unreasonable effectiveness of FedAvg that contradicts the previous theoretical predictions.
  arXiv  Detail & Related papers  (2022-06-09T18:25:25Z)
• Efficient CDF Approximations for Normalizing Flows [64.60846767084877]
  We build upon the diffeomorphic properties of normalizing flows to estimate the cumulative distribution function (CDF) over a closed region. Our experiments on popular flow architectures and UCI datasets show a marked improvement in sample efficiency as compared to traditional estimators.
  arXiv  Detail & Related papers  (2022-02-23T06:11:49Z)
• Localisation in quasiperiodic chains: a theory based on convergence of local propagators [68.8204255655161]
  We present a theory of localisation in quasiperiodic chains with nearest-neighbour hoppings, based on the convergence of local propagators. Analysing the convergence of these continued fractions, localisation or its absence can be determined, yielding in turn the critical points and mobility edges. Results are exemplified by analysing the theory for three quasiperiodic models covering a range of behaviour.
  arXiv  Detail & Related papers  (2021-02-18T16:19:52Z)
• Binary Classification of Gaussian Mixtures: Abundance of Support Vectors, Benign Overfitting and Regularization [39.35822033674126]
  We study binary linear classification under a generative Gaussian mixture model. We derive novel non-asymptotic bounds on the classification error of the latter. Our results extend to a noisy model with constant probability noise flips.
  arXiv  Detail & Related papers  (2020-11-18T07:59:55Z)
• Reducing the Variance of Variational Estimates of Mutual Information by Limiting the Critic's Hypothesis Space to RKHS [0.0]
  Mutual information (MI) is an information-theoretic measure of dependency between two random variables. Recent methods realize parametric probability distributions or critic as a neural network to approximate unknown density ratios. We argue that the high variance characteristic is due to the uncontrolled complexity of the critic's hypothesis space.
  arXiv  Detail & Related papers  (2020-11-17T14:32:48Z)
• On Localized Discrepancy for Domain Adaptation [146.4580736832752]
  This paper studies the localized discrepancies defined on the hypothesis space after localization. Their values will be different if we exchange the two domains, thus can reveal asymmetric transfer difficulties.
  arXiv  Detail & Related papers  (2020-08-14T08:30:02Z)
• Linear Last-iterate Convergence in Constrained Saddle-point Optimization [48.44657553192801]
  We significantly expand the understanding of last-rate uniqueness for Optimistic Gradient Descent Ascent (OGDA) and Optimistic Multiplicative Weights Update (OMWU) We show that when the equilibrium is unique, linear lastiterate convergence is achieved with a learning rate whose value is set to a universal constant. We show that bilinear games over any polytope satisfy this condition and OGDA converges exponentially fast even without the unique equilibrium assumption.
  arXiv  Detail & Related papers  (2020-06-16T20:53:04Z)

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.