N Timor, G Vardi, O Shamir - International Conference on …, 2023 - proceedings.mlr.press
We study the conjectured relationship between the implicit regularization in neural networks, trained with gradient-based methods, and rank minimization of their weight matrices …
A Jacot - The Eleventh International Conference on Learning …, 2023 - openreview.net
We show that the representation cost of fully connected neural networks with homogeneous nonlinearities-which describes the implicit bias in function space of networks with $ L_2 …
A Jacot - Advances in Neural Information Processing …, 2023 - proceedings.neurips.cc
Previous work has shown that DNNs withlarge depth $ L $ and $ L_ {2} $-regularization are biased towards learninglow-dimensional representations of the inputs, which can be …
This paper presents a framework for smooth optimization of objectives with ℓq and ℓp, q regularization for (structured) sparsity. Finding solutions to these non-smooth and possibly …
This paper explores the implicit bias of overparameterized neural networks of depth greater than two layers. Our framework considers a family of networks of varying depths that all have …
We study the loss surface of DNNs with $ L_ {2} $ regularization. Weshow that the loss in terms of the parameters can be reformulatedinto a loss in terms of the layerwise activations …
T Ergen, M Pilanci - Advances in Neural Information …, 2024 - proceedings.neurips.cc
Understanding the fundamental principles behind the success of deep neural networks is one of the most important open questions in the current literature. To this end, we study the …
We provide a function space characterization of the inductive bias resulting from minimizing the $\ell_2 $ norm of the weights in multi-channel convolutional neural networks with linear …
A fundamental problem in machine learning is to understand how neural networks make accurate predictions, while seemingly bypassing the curse of dimensionality. A possible …