Training invariances and the low-rank phenomenon: beyond linear networks

• URL: http://arxiv.org/abs/2201.11968v1
• Date: Fri, 28 Jan 2022 07:31:19 GMT
• Title: Training invariances and the low-rank phenomenon: beyond linear networks
• Authors: Thien Le, Stefanie Jegelka
• Abstract summary: We show that when one trains a deep linear network with logistic or exponential loss on linearly separable data, the weights converge to rank-$1$ matrices. This is the first time a low-rank phenomenon is proven rigorously for nonlinear ReLU-activated feedforward networks. Our proof relies on a specific decomposition of the network into a multilinear function and another ReLU network whose weights are constant under a certain parameter directional convergence.
• Score: 44.02161831977037
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The implicit bias induced by the training of neural networks has become a topic of rigorous study. In the limit of gradient flow and gradient descent with appropriate step size, it has been shown that when one trains a deep linear network with logistic or exponential loss on linearly separable data, the weights converge to rank-$1$ matrices. In this paper, we extend this theoretical result to the much wider class of nonlinear ReLU-activated feedforward networks containing fully-connected layers and skip connections. To the best of our knowledge, this is the first time a low-rank phenomenon is proven rigorously for these architectures, and it reflects empirical results in the literature. The proof relies on specific local training invariances, sometimes referred to as alignment, which we show to hold for a wide set of ReLU architectures. Our proof relies on a specific decomposition of the network into a multilinear function and another ReLU network whose weights are constant under a certain parameter directional convergence.

Related papers

• Minimum-Norm Interpolation Under Covariate Shift [14.863831433459902]
  In-distribution research on high-dimensional linear regression has led to the identification of a phenomenon known as textitbenign overfitting We prove the first non-asymptotic excess risk bounds for benignly-overfit linear interpolators in the transfer learning setting.
  arXiv  Detail & Related papers  (2024-03-31T01:41:57Z)
• Convergence Analysis for Learning Orthonormal Deep Linear Neural Networks [27.29463801531576]
  We provide convergence analysis for training orthonormal deep linear neural networks. Our results shed light on how increasing the number of hidden layers can impact the convergence speed.
  arXiv  Detail & Related papers  (2023-11-24T18:46:54Z)
• Implicit Bias in Leaky ReLU Networks Trained on High-Dimensional Data [63.34506218832164]
  In this work, we investigate the implicit bias of gradient flow and gradient descent in two-layer fully-connected neural networks with ReLU activations. For gradient flow, we leverage recent work on the implicit bias for homogeneous neural networks to show that leakyally, gradient flow produces a neural network with rank at most two. For gradient descent, provided the random variance is small enough, we show that a single step of gradient descent suffices to drastically reduce the rank of the network, and that the rank remains small throughout training.
  arXiv  Detail & Related papers  (2022-10-13T15:09:54Z)
• Slimmable Networks for Contrastive Self-supervised Learning [69.9454691873866]
  Self-supervised learning makes significant progress in pre-training large models, but struggles with small models. We introduce another one-stage solution to obtain pre-trained small models without the need for extra teachers. A slimmable network consists of a full network and several weight-sharing sub-networks, which can be pre-trained once to obtain various networks.
  arXiv  Detail & Related papers  (2022-09-30T15:15:05Z)
• Convergence and Implicit Regularization Properties of Gradient Descent for Deep Residual Networks [7.090165638014331]
  We prove linear convergence of gradient descent to a global minimum for the training of deep residual networks with constant layer width and smooth activation function. We show that the trained weights, as a function of the layer index, admits a scaling limit which is H"older continuous as the depth of the network tends to infinity.
  arXiv  Detail & Related papers  (2022-04-14T22:50:28Z)
• Mean-field Analysis of Piecewise Linear Solutions for Wide ReLU Networks [83.58049517083138]
  We consider a two-layer ReLU network trained via gradient descent. We show that SGD is biased towards a simple solution. We also provide empirical evidence that knots at locations distinct from the data points might occur.
  arXiv  Detail & Related papers  (2021-11-03T15:14:20Z)
• Over-parametrized neural networks as under-determined linear systems [31.69089186688224]
  We show that it is unsurprising simple neural networks can achieve zero training loss. We show that kernels typically associated with the ReLU activation function have fundamental flaws. We propose new activation functions that avoid the pitfalls of ReLU in that they admit zero training loss solutions for any set of distinct data points.
  arXiv  Detail & Related papers  (2020-10-29T21:43:00Z)
• Directional convergence and alignment in deep learning [38.73942298289583]
  We show that although the minimizers of cross-entropy and related classification losses at infinity, network weights learn by gradient flow converge in direction. This proof holds for deep homogeneous networks allowing for ReLU, max-pooling, linear, and convolutional layers.
  arXiv  Detail & Related papers  (2020-06-11T17:50:11Z)
• Revealing the Structure of Deep Neural Networks via Convex Duality [70.15611146583068]
  We study regularized deep neural networks (DNNs) and introduce a convex analytic framework to characterize the structure of hidden layers. We show that a set of optimal hidden layer weights for a norm regularized training problem can be explicitly found as the extreme points of a convex set. We apply the same characterization to deep ReLU networks with whitened data and prove the same weight alignment holds.
  arXiv  Detail & Related papers  (2020-02-22T21:13:44Z)
• 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.