An Analysis of Constant Step Size SGD in the Non-convex Regime: Asymptotic Normality and Bias

• URL: http://arxiv.org/abs/2006.07904v2
• Date: Thu, 30 Jul 2020 01:27:47 GMT
• Title: An Analysis of Constant Step Size SGD in the Non-convex Regime: Asymptotic Normality and Bias
• Authors: Lu Yu, Krishnakumar Balasubramanian, Stanislav Volgushev, and Murat A. Erdogdu
• Abstract summary: Structured non- learning problems, for which critical points have favorable statistical properties, arise frequently in statistical machine learning. We show that the SGD algorithm is widely used in practice.
• Score: 17.199063087458907
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Structured non-convex learning problems, for which critical points have favorable statistical properties, arise frequently in statistical machine learning. Algorithmic convergence and statistical estimation rates are well-understood for such problems. However, quantifying the uncertainty associated with the underlying training algorithm is not well-studied in the non-convex setting. In order to address this shortcoming, in this work, we establish an asymptotic normality result for the constant step size stochastic gradient descent (SGD) algorithm--a widely used algorithm in practice. Specifically, based on the relationship between SGD and Markov Chains [DDB19], we show that the average of SGD iterates is asymptotically normally distributed around the expected value of their unique invariant distribution, as long as the non-convex and non-smooth objective function satisfies a dissipativity property. We also characterize the bias between this expected value and the critical points of the objective function under various local regularity conditions. Together, the above two results could be leveraged to construct confidence intervals for non-convex problems that are trained using the SGD algorithm.

Related papers

• Stability and Generalization of the Decentralized Stochastic Gradient Descent Ascent Algorithm [80.94861441583275]
  We investigate the complexity of the generalization bound of the decentralized gradient descent (D-SGDA) algorithm. Our results analyze the impact of different top factors on the generalization of D-SGDA. We also balance it with the generalization to obtain the optimal convex-concave setting.
  arXiv  Detail & Related papers  (2023-10-31T11:27:01Z)
• Accelerated stochastic approximation with state-dependent noise [7.623467689146604]
  We consider a class of smooth convex optimization problems under general assumptions on the quadratic noise in the gradient observation. Such problems naturally arise in a variety of applications, in particular, in the well-known generalized linear regression problem in statistics. We show that both SAGD and SGE, under appropriate conditions, achieve the optimal convergence rate.
  arXiv  Detail & Related papers  (2023-07-04T06:06:10Z)
• 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)
• On the Convergence of mSGD and AdaGrad for Stochastic Optimization [0.696125353550498]
  convex descent (SGD) has been intensively developed and extensively applied in machine learning in the past decade. Some modified SGD-type algorithms, which outperform the SGD in many competitions and applications in terms of convergence rate and accuracy, such as momentum-based SGD (mSGD) and adaptive gradient optimization (AdaGrad) We focus on convergence analysis of mSGD and AdaGrad for any smooth (possibly non-possibly non-possibly non-possibly) loss functions in machine learning.
  arXiv  Detail & Related papers  (2022-01-26T22:02:21Z)
• Nonconvex Stochastic Scaled-Gradient Descent and Generalized Eigenvector Problems [98.34292831923335]
  Motivated by the problem of online correlation analysis, we propose the emphStochastic Scaled-Gradient Descent (SSD) algorithm. We bring these ideas together in an application to online correlation analysis, deriving for the first time an optimal one-time-scale algorithm with an explicit rate of local convergence to normality.
  arXiv  Detail & Related papers  (2021-12-29T18:46:52Z)
• On the Double Descent of Random Features Models Trained with SGD [78.0918823643911]
  We study properties of random features (RF) regression in high dimensions optimized by gradient descent (SGD) We derive precise non-asymptotic error bounds of RF regression under both constant and adaptive step-size SGD setting. We observe the double descent phenomenon both theoretically and empirically.
  arXiv  Detail & Related papers  (2021-10-13T17:47:39Z)
• Benign Overfitting of Constant-Stepsize SGD for Linear Regression [122.70478935214128]
  inductive biases are central in preventing overfitting empirically. This work considers this issue in arguably the most basic setting: constant-stepsize SGD for linear regression. We reflect on a number of notable differences between the algorithmic regularization afforded by (unregularized) SGD in comparison to ordinary least squares.
  arXiv  Detail & Related papers  (2021-03-23T17:15:53Z)
• Stochastic optimization with momentum: convergence, fluctuations, and traps avoidance [0.0]
  In this paper, a general optimization procedure is studied, unifying several variants of the gradient descent such as, among others, the heavy ball method, the Nesterov Accelerated Gradient (S-NAG), and the widely used Adam method. The avoidance is studied as a noisy discretization of a non-autonomous ordinary differential equation.
  arXiv  Detail & Related papers  (2020-12-07T19:14:49Z)
• Practical Precoding via Asynchronous Stochastic Successive Convex Approximation [8.808993671472349]
  We consider optimization of a smooth non-studied loss function with a convex non-smooth regularizer. In this work, we take a closer look at the SCA algorithm and develop its asynchronous variant for resource allocation in wireless networks.
  arXiv  Detail & Related papers  (2020-10-03T13:53:30Z)
• Instability, Computational Efficiency and Statistical Accuracy [101.32305022521024]
  We develop a framework that yields statistical accuracy based on interplay between the deterministic convergence rate of the algorithm at the population level, and its degree of (instability) when applied to an empirical object based on $n$ samples. We provide applications of our general results to several concrete classes of models, including Gaussian mixture estimation, non-linear regression models, and informative non-response models.
  arXiv  Detail & Related papers  (2020-05-22T22:30:52Z)

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.