The loss landscape of deep linear neural networks: a second-order analysis

• URL: http://arxiv.org/abs/2107.13289v3
• Date: Wed, 25 Sep 2024 07:38:43 GMT
• Title: The loss landscape of deep linear neural networks: a second-order analysis
• Authors: El Mehdi Achour, François Malgouyres, Sébastien Gerchinovitz,
• Abstract summary: We study the optimization landscape of deep linear neural networks with the square loss. We characterize, among all critical points, which are global minimizers, strict saddle points, and non-strict saddle points.
• Score: 9.85879905918703
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We study the optimization landscape of deep linear neural networks with the square loss. It is known that, under weak assumptions, there are no spurious local minima and no local maxima. However, the existence and diversity of non-strict saddle points, which can play a role in first-order algorithms' dynamics, have only been lightly studied. We go a step further with a full analysis of the optimization landscape at order 2. We characterize, among all critical points, which are global minimizers, strict saddle points, and non-strict saddle points. We enumerate all the associated critical values. The characterization is simple, involves conditions on the ranks of partial matrix products, and sheds some light on global convergence or implicit regularization that have been proved or observed when optimizing linear neural networks. In passing, we provide an explicit parameterization of the set of all global minimizers and exhibit large sets of strict and non-strict saddle points.

Related papers

• Stochastic Zeroth-Order Optimization under Strongly Convexity and Lipschitz Hessian: Minimax Sample Complexity [59.75300530380427]
  We consider the problem of optimizing second-order smooth and strongly convex functions where the algorithm is only accessible to noisy evaluations of the objective function it queries. We provide the first tight characterization for the rate of the minimax simple regret by developing matching upper and lower bounds.
  arXiv  Detail & Related papers  (2024-06-28T02:56:22Z)
• A Mean-Field Analysis of Neural Stochastic Gradient Descent-Ascent for Functional Minimax Optimization [90.87444114491116]
  This paper studies minimax optimization problems defined over infinite-dimensional function classes of overparametricized two-layer neural networks. We address (i) the convergence of the gradient descent-ascent algorithm and (ii) the representation learning of the neural networks. Results show that the feature representation induced by the neural networks is allowed to deviate from the initial one by the magnitude of $O(alpha-1)$, measured in terms of the Wasserstein distance.
  arXiv  Detail & Related papers  (2024-04-18T16:46:08Z)
• The Inductive Bias of Flatness Regularization for Deep Matrix Factorization [58.851514333119255]
  This work takes the first step toward understanding the inductive bias of the minimum trace of the Hessian solutions in deep linear networks. We show that for all depth greater than one, with the standard Isometry Property (RIP) on the measurements, minimizing the trace of Hessian is approximately equivalent to minimizing the Schatten 1-norm of the corresponding end-to-end matrix parameters.
  arXiv  Detail & Related papers  (2023-06-22T23:14:57Z)
• On the Omnipresence of Spurious Local Minima in Certain Neural Network Training Problems [0.0]
  We study the loss landscape of training problems for deep artificial neural networks with a one-dimensional real output. It is shown that such problems possess a continuum of spurious (i.e., not globally optimal) local minima for all target functions that are not affine.
  arXiv  Detail & Related papers  (2022-02-23T14:41:54Z)
• Global Convergence Analysis of Deep Linear Networks with A One-neuron Layer [18.06634056613645]
  We consider optimizing deep linear networks which have a layer with one neuron under quadratic loss. We describe the convergent point of trajectories with arbitrary starting point under flow. We show specific convergence rates of trajectories that converge to the global gradientr by stages.
  arXiv  Detail & Related papers  (2022-01-08T04:44:59Z)
• Landscape analysis for shallow ReLU neural networks: complete classification of critical points for affine target functions [3.9103337761169947]
  We provide a complete classification of the critical points in the case where the target function is affine. Our approach builds on a careful analysis of the different types of hidden neurons that can occur in a ReLU neural network.
  arXiv  Detail & Related papers  (2021-03-19T17:35:01Z)
• Efficient Methods for Structured Nonconvex-Nonconcave Min-Max Optimization [98.0595480384208]
  We propose a generalization extraient spaces which converges to a stationary point. The algorithm applies not only to general $p$-normed spaces, but also to general $p$-dimensional vector spaces.
  arXiv  Detail & Related papers  (2020-10-31T21:35:42Z)
• The Hidden Convex Optimization Landscape of Two-Layer ReLU Neural Networks: an Exact Characterization of the Optimal Solutions [51.60996023961886]
  We prove that finding all globally optimal two-layer ReLU neural networks can be performed by solving a convex optimization program with cone constraints. Our analysis is novel, characterizes all optimal solutions, and does not leverage duality-based analysis which was recently used to lift neural network training into convex spaces.
  arXiv  Detail & Related papers  (2020-06-10T15:38:30Z)
• The Effects of Mild Over-parameterization on the Optimization Landscape of Shallow ReLU Neural Networks [36.35321290763711]
  We prove that the objective is strongly convex around the global minima when the teacher and student networks possess the same number of neurons. For the non-global minima, we prove that adding even just a single neuron will turn a non-global minimum into a saddle point.
  arXiv  Detail & Related papers  (2020-06-01T15:13:15Z)
• Convex Geometry and Duality of Over-parameterized Neural Networks [70.15611146583068]
  We develop a convex analytic approach to analyze finite width two-layer ReLU networks. We show that an optimal solution to the regularized training problem can be characterized as extreme points of a convex set. In higher dimensions, we show that the training problem can be cast as a finite dimensional convex problem with infinitely many constraints.
  arXiv  Detail & Related papers  (2020-02-25T23:05:33Z)

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.