Towards Understanding Generalization via Decomposing Excess Risk Dynamics

• URL: http://arxiv.org/abs/2106.06153v1
• Date: Fri, 11 Jun 2021 03:42:45 GMT
• Title: Towards Understanding Generalization via Decomposing Excess Risk Dynamics
• Authors: Jiaye Teng, Jianhao Ma, Yang Yuan
• Abstract summary: We analyze the generalization dynamics to derive algorithm-dependent bounds, e.g., stability. Inspired by the observation that neural networks show a slow convergence rate when fitting noise, we propose decomposing the excess risk dynamics. Under the decomposition framework, the new bound accords better with the theoretical and empirical evidence compared to the stability-based bound and uniform convergence bound.
• Score: 13.4379473119565
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Generalization is one of the critical issues in machine learning. However, traditional methods like uniform convergence are not powerful enough to fully explain generalization because they may yield vacuous bounds even in overparameterized linear regression regimes. An alternative solution is to analyze the generalization dynamics to derive algorithm-dependent bounds, e.g., stability. Unfortunately, the stability-based bound is still far from explaining the remarkable generalization ability of neural networks due to the coarse-grained analysis of the signal and noise. Inspired by the observation that neural networks show a slow convergence rate when fitting noise, we propose decomposing the excess risk dynamics and applying stability-based bound only on the variance part (which measures how the model performs on pure noise). We provide two applications for the framework, including a linear case (overparameterized linear regression with gradient descent) and a non-linear case (matrix recovery with gradient flow). Under the decomposition framework, the new bound accords better with the theoretical and empirical evidence compared to the stability-based bound and uniform convergence bound.

Related papers

• Generalization in Kernel Regression Under Realistic Assumptions [41.345620270267446]
  We provide rigorous bounds for common kernels and for any amount of regularization, noise, any input dimension, and any number of samples. Our results imply benign overfitting in high input dimensions, nearly tempered overfitting in fixed dimensions, and explicit convergence rates for regularized regression. As a by-product, we obtain time-dependent bounds for neural networks trained in the kernel regime.
  arXiv  Detail & Related papers  (2023-12-26T10:55:20Z)
• Stable Nonconvex-Nonconcave Training via Linear Interpolation [51.668052890249726]
  This paper presents a theoretical analysis of linearahead as a principled method for stabilizing (large-scale) neural network training. We argue that instabilities in the optimization process are often caused by the nonmonotonicity of the loss landscape and show how linear can help by leveraging the theory of nonexpansive operators.
  arXiv  Detail & Related papers  (2023-10-20T12:45:12Z)
• Implicit Regularization for Group Sparsity [33.487964460794764]
  We show that gradient descent over the squared regression loss, without any explicit regularization, biases towards solutions with a group sparsity structure. We analyze the gradient dynamics of the corresponding regression problem in the general noise setting and obtain minimax-optimal error rates. In the degenerate case of size-one groups, our approach gives rise to a new algorithm for sparse linear regression.
  arXiv  Detail & Related papers  (2023-01-29T20:54:03Z)
• 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)
• Towards Data-Algorithm Dependent Generalization: a Case Study on Overparameterized Linear Regression [19.047997113063147]
  We introduce a notion called data-algorithm compatibility, which considers the generalization behavior of the entire data-dependent training trajectory. We perform a data-dependent trajectory analysis and derive a sufficient condition for compatibility in such a setting.
  arXiv  Detail & Related papers  (2022-02-12T12:42:36Z)
• A Priori Denoising Strategies for Sparse Identification of Nonlinear Dynamical Systems: A Comparative Study [68.8204255655161]
  We investigate and compare the performance of several local and global smoothing techniques to a priori denoise the state measurements. We show that, in general, global methods, which use the entire measurement data set, outperform local methods, which employ a neighboring data subset around a local point.
  arXiv  Detail & Related papers  (2022-01-29T23:31:25Z)
• 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)
• Statistical optimality and stability of tangent transform algorithms in logit models [6.9827388859232045]
  We provide conditions on the data generating process to derive non-asymptotic upper bounds to the risk incurred by the logistical optima. In particular, we establish local variation of the algorithm without any assumptions on the data-generating process. We explore a special case involving a semi-orthogonal design under which a global convergence is obtained.
  arXiv  Detail & Related papers  (2020-10-25T05:15:13Z)
• Multiplicative noise and heavy tails in stochastic optimization [62.993432503309485]
  empirical optimization is central to modern machine learning, but its role in its success is still unclear. We show that it commonly arises in parameters of discrete multiplicative noise due to variance. A detailed analysis is conducted in which we describe on key factors, including recent step size, and data, all exhibit similar results on state-of-the-art neural network models.
  arXiv  Detail & Related papers  (2020-06-11T09:58:01Z)
• On dissipative symplectic integration with applications to gradient-based optimization [77.34726150561087]
  We propose a geometric framework in which discretizations can be realized systematically. We show that a generalization of symplectic to nonconservative and in particular dissipative Hamiltonian systems is able to preserve rates of convergence up to a controlled error.
  arXiv  Detail & Related papers  (2020-04-15T00:36:49Z)

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.