Nonasymptotic theory for two-layer neural networks: Beyond the bias-variance trade-off

• URL: http://arxiv.org/abs/2106.04795v2
• Date: Sun, 30 Jul 2023 09:41:17 GMT
• Title: Nonasymptotic theory for two-layer neural networks: Beyond the bias-variance trade-off
• Authors: Huiyuan Wang and Wei Lin
• Abstract summary: We present a nonasymptotic generalization theory for two-layer neural networks with ReLU activation function. We show that overparametrized random feature models suffer from the curse of dimensionality and thus are suboptimal.
• Score: 10.182922771556742
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Large neural networks have proved remarkably effective in modern deep learning practice, even in the overparametrized regime where the number of active parameters is large relative to the sample size. This contradicts the classical perspective that a machine learning model must trade off bias and variance for optimal generalization. To resolve this conflict, we present a nonasymptotic generalization theory for two-layer neural networks with ReLU activation function by incorporating scaled variation regularization. Interestingly, the regularizer is equivalent to ridge regression from the angle of gradient-based optimization, but plays a similar role to the group lasso in controlling the model complexity. By exploiting this "ridge-lasso duality," we obtain new prediction bounds for all network widths, which reproduce the double descent phenomenon. Moreover, the overparametrized minimum risk is lower than its underparametrized counterpart when the signal is strong, and is nearly minimax optimal over a suitable class of functions. By contrast, we show that overparametrized random feature models suffer from the curse of dimensionality and thus are suboptimal.

Related papers

• The Asymmetric Maximum Margin Bias of Quasi-Homogeneous Neural Networks [26.58848653965855]
  We introduce the class of quasi-homogeneous models, which is expressive enough to describe nearly all neural networks with homogeneous activations. We find that gradient flow implicitly favors a subset of the parameters, unlike in the case of a homogeneous model where all parameters are treated equally.
  arXiv  Detail & Related papers  (2022-10-07T21:14:09Z)
• Phenomenology of Double Descent in Finite-Width Neural Networks [29.119232922018732]
  Double descent delineates the behaviour of models depending on the regime they belong to. We use influence functions to derive suitable expressions of the population loss and its lower bound. Building on our analysis, we investigate how the loss function affects double descent.
  arXiv  Detail & Related papers  (2022-03-14T17:39:49Z)
• Multi-scale Feature Learning Dynamics: Insights for Double Descent [71.91871020059857]
  We study the phenomenon of "double descent" of the generalization error. We find that double descent can be attributed to distinct features being learned at different scales.
  arXiv  Detail & Related papers  (2021-12-06T18:17:08Z)
• The Interplay Between Implicit Bias and Benign Overfitting in Two-Layer Linear Networks [51.1848572349154]
  neural network models that perfectly fit noisy data can generalize well to unseen test data. We consider interpolating two-layer linear neural networks trained with gradient flow on the squared loss and derive bounds on the excess risk.
  arXiv  Detail & Related papers  (2021-08-25T22:01:01Z)
• On the Role of Optimization in Double Descent: A Least Squares Study [30.44215064390409]
  We show an excess risk bound for the descent gradient solution of the least squares objective. We find that in case of noiseless regression, double descent is explained solely by optimization-related quantities. We empirically explore if our predictions hold for neural networks.
  arXiv  Detail & Related papers  (2021-07-27T09:13:11Z)
• Towards an Understanding of Benign Overfitting in Neural Networks [104.2956323934544]
  Modern machine learning models often employ a huge number of parameters and are typically optimized to have zero training loss. We examine how these benign overfitting phenomena occur in a two-layer neural network setting. We show that it is possible for the two-layer ReLU network interpolator to achieve a near minimax-optimal learning rate.
  arXiv  Detail & Related papers  (2021-06-06T19:08:53Z)
• Provable Model-based Nonlinear Bandit and Reinforcement Learning: Shelve Optimism, Embrace Virtual Curvature [61.22680308681648]
  We show that global convergence is statistically intractable even for one-layer neural net bandit with a deterministic reward. For both nonlinear bandit and RL, the paper presents a model-based algorithm, Virtual Ascent with Online Model Learner (ViOL)
  arXiv  Detail & Related papers  (2021-02-08T12:41:56Z)
• Optimizing Mode Connectivity via Neuron Alignment [84.26606622400423]
  Empirically, the local minima of loss functions can be connected by a learned curve in model space along which the loss remains nearly constant. We propose a more general framework to investigate effect of symmetry on landscape connectivity by accounting for the weight permutations of networks being connected.
  arXiv  Detail & Related papers  (2020-09-05T02:25:23Z)
• The Neural Tangent Kernel in High Dimensions: Triple Descent and a Multi-Scale Theory of Generalization [34.235007566913396]
  Modern deep learning models employ considerably more parameters than required to fit the training data. Whereas conventional statistical wisdom suggests such models should drastically overfit, in practice these models generalize remarkably well. An emerging paradigm for describing this unexpected behavior is in terms of a emphdouble descent curve. We provide a precise high-dimensional analysis of generalization with the Neural Tangent Kernel, which characterizes the behavior of wide neural networks with gradient descent.
  arXiv  Detail & Related papers  (2020-08-15T20:55:40Z)
• Optimal Regularization Can Mitigate Double Descent [29.414119906479954]
  We study whether the double-descent phenomenon can be avoided by using optimal regularization. We demonstrate empirically that optimally-tuned $ell$ regularization can double descent for more general models, including neural networks.
  arXiv  Detail & Related papers  (2020-03-04T05:19:09Z)
• Kernel and Rich Regimes in Overparametrized Models [69.40899443842443]
  We show that gradient descent on overparametrized multilayer networks can induce rich implicit biases that are not RKHS norms. We also demonstrate this transition empirically for more complex matrix factorization models and multilayer non-linear networks.
  arXiv  Detail & Related papers  (2020-02-20T15:43:02Z)

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.