The Optimality of (Accelerated) SGD for High-Dimensional Quadratic Optimization

• URL: http://arxiv.org/abs/2409.09745v1
• Date: Sun, 15 Sep 2024 14:20:03 GMT
• Title: The Optimality of (Accelerated) SGD for High-Dimensional Quadratic Optimization
• Authors: Haihan Zhang, Yuanshi Liu, Qianwen Chen, Cong Fang,
• Abstract summary: gradient descent (SGD) is a widely used algorithm in machine learning, particularly for neural network training. Recent studies on SGD for canonical quadratic optimization or linear regression show it attains well generalization under suitable high-dimensional settings. This paper investigates SGD with two essential components in practice: exponentially decaying step size schedule and momentum.
• Score: 4.7256945641654164
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Stochastic gradient descent (SGD) is a widely used algorithm in machine learning, particularly for neural network training. Recent studies on SGD for canonical quadratic optimization or linear regression show it attains well generalization under suitable high-dimensional settings. However, a fundamental question -- for what kinds of high-dimensional learning problems SGD and its accelerated variants can achieve optimality has yet to be well studied. This paper investigates SGD with two essential components in practice: exponentially decaying step size schedule and momentum. We establish the convergence upper bound for momentum accelerated SGD (ASGD) and propose concrete classes of learning problems under which SGD or ASGD achieves min-max optimal convergence rates. The characterization of the target function is based on standard power-law decays in (functional) linear regression. Our results unveil new insights for understanding the learning bias of SGD: (i) SGD is efficient in learning ``dense'' features where the corresponding weights are subject to an infinity norm constraint; (ii) SGD is efficient for easy problem without suffering from the saturation effect; (iii) momentum can accelerate the convergence rate by order when the learning problem is relatively hard. To our knowledge, this is the first work to clearly identify the optimal boundary of SGD versus ASGD for the problem under mild settings.

Related papers

• Non-convergence to global minimizers in data driven supervised deep learning: Adam and stochastic gradient descent optimization provably fail to converge to global minimizers in the training of deep neural networks with ReLU activation [3.6185342807265415]
  It remains an open problem of research to explain the success and the limitations of SGD methods in rigorous theoretical terms. In this work we prove for a large class of SGD methods that the considered does with high probability not converge to global minimizers of the optimization problem. The general non-convergence results of this work do not only apply to the plain vanilla standard SGD method but also to a large class of accelerated and adaptive SGD methods.
  arXiv  Detail & Related papers  (2024-10-14T14:11:37Z)
• A Stochastic Approach to Bi-Level Optimization for Hyperparameter Optimization and Meta Learning [74.80956524812714]
  We tackle the general differentiable meta learning problem that is ubiquitous in modern deep learning. These problems are often formalized as Bi-Level optimizations (BLO) We introduce a novel perspective by turning a given BLO problem into a ii optimization, where the inner loss function becomes a smooth distribution, and the outer loss becomes an expected loss over the inner distribution.
  arXiv  Detail & Related papers  (2024-10-14T12:10:06Z)
• Stability and Generalization Analysis of Gradient Methods for Shallow Neural Networks [59.142826407441106]
  We study the generalization behavior of shallow neural networks (SNNs) by leveraging the concept of algorithmic stability. We consider gradient descent (GD) and gradient descent (SGD) to train SNNs, for both of which we develop consistent excess bounds.
  arXiv  Detail & Related papers  (2022-09-19T18:48:00Z)
• Implicit Regularization or Implicit Conditioning? Exact Risk Trajectories of SGD in High Dimensions [26.782342518986503]
  gradient descent (SGD) is a pillar of modern machine learning, serving as the go-to optimization algorithm for a diverse array of problems. We show how to adapt the HSGD formalism to include streaming SGD, which allows us to produce an exact prediction for the excess risk of multi-pass SGD relative to that of streaming SGD.
  arXiv  Detail & Related papers  (2022-06-15T02:32:26Z)
• Benign Underfitting of Stochastic Gradient Descent [72.38051710389732]
  We study to what extent may gradient descent (SGD) be understood as a "conventional" learning rule that achieves generalization performance by obtaining a good fit training data. We analyze the closely related with-replacement SGD, for which an analogous phenomenon does not occur and prove that its population risk does in fact converge at the optimal rate.
  arXiv  Detail & Related papers  (2022-02-27T13:25:01Z)
• Stabilizing Spiking Neuron Training [3.335932527835653]
  spiking Neuromorphic Computing uses binary activity to improve Artificial Intelligence energy efficiency. It remains unclear how to determine the best SG for a given task and network. We show how it can be used to reduce the need for extensive grid-search of dampening, sharpness and tail-fatness of the SG.
  arXiv  Detail & Related papers  (2022-02-01T09:10:57Z)
• The Benefits of Implicit Regularization from SGD in Least Squares Problems [116.85246178212616]
  gradient descent (SGD) exhibits strong algorithmic regularization effects in practice. We make comparisons of the implicit regularization afforded by (unregularized) average SGD with the explicit regularization of ridge regression.
  arXiv  Detail & Related papers  (2021-08-10T09:56:47Z)
• Understanding Long Range Memory Effects in Deep Neural Networks [10.616643031188248]
  textitstochastic gradient descent (SGD) is of fundamental importance in deep learning. In this study, we argue that SGN is neither Gaussian nor stable. Instead, we propose that SGD can be viewed as a discretization of an SDE driven by textitfractional Brownian motion (FBM)
  arXiv  Detail & Related papers  (2021-05-05T13:54:26Z)
• Direction Matters: On the Implicit Bias of Stochastic Gradient Descent with Moderate Learning Rate [105.62979485062756]
  This paper attempts to characterize the particular regularization effect of SGD in the moderate learning rate regime. We show that SGD converges along the large eigenvalue directions of the data matrix, while GD goes after the small eigenvalue directions.
  arXiv  Detail & Related papers  (2020-11-04T21:07:52Z)
• Detached Error Feedback for Distributed SGD with Random Sparsification [98.98236187442258]
  Communication bottleneck has been a critical problem in large-scale deep learning. We propose a new distributed error feedback (DEF) algorithm, which shows better convergence than error feedback for non-efficient distributed problems. We also propose DEFA to accelerate the generalization of DEF, which shows better bounds than DEF.
  arXiv  Detail & Related papers  (2020-04-11T03:50:59Z)

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.