Understanding the training of infinitely deep and wide ResNets with Conditional Optimal Transport
- URL: http://arxiv.org/abs/2403.12887v1
- Date: Tue, 19 Mar 2024 16:34:31 GMT
- Title: Understanding the training of infinitely deep and wide ResNets with Conditional Optimal Transport
- Authors: Raphaël Barboni, Gabriel Peyré, François-Xavier Vialard,
- Abstract summary: We show that the gradient flow for deep neural networks converges arbitrarily at a distance ofr.
This is done by relying on the theory of gradient distance of finite width in spaces.
- Score: 26.47265060394168
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: We study the convergence of gradient flow for the training of deep neural networks. If Residual Neural Networks are a popular example of very deep architectures, their training constitutes a challenging optimization problem due notably to the non-convexity and the non-coercivity of the objective. Yet, in applications, those tasks are successfully solved by simple optimization algorithms such as gradient descent. To better understand this phenomenon, we focus here on a ``mean-field'' model of infinitely deep and arbitrarily wide ResNet, parameterized by probability measures over the product set of layers and parameters and with constant marginal on the set of layers. Indeed, in the case of shallow neural networks, mean field models have proven to benefit from simplified loss-landscapes and good theoretical guarantees when trained with gradient flow for the Wasserstein metric on the set of probability measures. Motivated by this approach, we propose to train our model with gradient flow w.r.t. the conditional Optimal Transport distance: a restriction of the classical Wasserstein distance which enforces our marginal condition. Relying on the theory of gradient flows in metric spaces we first show the well-posedness of the gradient flow equation and its consistency with the training of ResNets at finite width. Performing a local Polyak-\L{}ojasiewicz analysis, we then show convergence of the gradient flow for well-chosen initializations: if the number of features is finite but sufficiently large and the risk is sufficiently small at initialization, the gradient flow converges towards a global minimizer. This is the first result of this type for infinitely deep and arbitrarily wide ResNets.
Related papers
- 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) - Implicit regularization in AI meets generalized hardness of
approximation in optimization -- Sharp results for diagonal linear networks [0.0]
We show sharp results for the implicit regularization imposed by the gradient flow of Diagonal Linear Networks.
We link this to the phenomenon of phase transitions in generalized hardness of approximation.
Non-sharpness of our results would imply that the GHA phenomenon would not occur for the basis pursuit optimization problem.
arXiv Detail & Related papers (2023-07-13T13:27:51Z) - Globally Optimal Training of Neural Networks with Threshold Activation
Functions [63.03759813952481]
We study weight decay regularized training problems of deep neural networks with threshold activations.
We derive a simplified convex optimization formulation when the dataset can be shattered at a certain layer of the network.
arXiv Detail & Related papers (2023-03-06T18:59:13Z) - 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) - Path Regularization: A Convexity and Sparsity Inducing Regularization
for Parallel ReLU Networks [75.33431791218302]
We study the training problem of deep neural networks and introduce an analytic approach to unveil hidden convexity in the optimization landscape.
We consider a deep parallel ReLU network architecture, which also includes standard deep networks and ResNets as its special cases.
arXiv Detail & Related papers (2021-10-18T18:00:36Z) - On the Global Convergence of Gradient Descent for multi-layer ResNets in
the mean-field regime [19.45069138853531]
First-order methods find the global optimum in the globalized regime.
We show that if the ResNet is sufficiently large, with depth width depending on the accuracy and confidence levels, first-order methods can find optimization that fit the data.
arXiv Detail & Related papers (2021-10-06T17:16:09Z) - Proxy Convexity: A Unified Framework for the Analysis of Neural Networks
Trained by Gradient Descent [95.94432031144716]
We propose a unified non- optimization framework for the analysis of a learning network.
We show that existing guarantees can be trained unified through gradient descent.
arXiv Detail & Related papers (2021-06-25T17:45:00Z) - Overparameterization of deep ResNet: zero loss and mean-field analysis [19.45069138853531]
Finding parameters in a deep neural network (NN) that fit data is a non optimization problem.
We show that a basic first-order optimization method (gradient descent) finds a global solution with perfect fit in many practical situations.
We give estimates of the depth and width needed to reduce the loss below a given threshold, with high probability.
arXiv Detail & Related papers (2021-05-30T02:46:09Z) - Modeling from Features: a Mean-field Framework for Over-parameterized
Deep Neural Networks [54.27962244835622]
This paper proposes a new mean-field framework for over- parameterized deep neural networks (DNNs)
In this framework, a DNN is represented by probability measures and functions over its features in the continuous limit.
We illustrate the framework via the standard DNN and the Residual Network (Res-Net) architectures.
arXiv Detail & Related papers (2020-07-03T01:37:16Z) - 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)
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.