paper-with-me

홈 › Papers

How (Implicit) Regularization of ReLU Neural Networks Characterizes the Learned Function -- Part II: the Multi-D Case of Two Layers with Random First Layer

2023-03-20 · Jakob Heiss, Josef Teichmann, Hanna Wutte

Randomized neural networks (randomized NNs), where only the terminal layer's weights are optimized constitute a powerful model class to reduce computational time in training the neural network model. At the same time, these models generalize surprisingly well in various regression and classification tasks. In this paper, we give an exact macroscopic characterization (i.e., a characterization in function space) of the generalization behavior of randomized, shallow NNs with ReLU activation (RSNs). We show that RSNs correspond to a generalized additive model (GAM)-typed regression in which infinitely many directions are considered: the infinite generalized additive model (IGAM). The IGAM is formalized as solution to an optimization problem in function space for a specific regularization functional and a fairly general loss. This work is an extension to multivariate NNs of prior work, where we showed how wide RSNs with ReLU activation behave like spline regression under certain conditions and if the input is one-dimensional.

📄 PDF Abstract BibTeX arXiv:2303.11454

Code (0)

등록된 구현이 없습니다.

Tasks

regression

Similar Papers 제목 키워드 기반

How Implicit Regularization of ReLU Neural Networks Characterizes the Learned Function -- Part I: the 1-D Case of Two Layers with Random First Layer

2019-11-07 · Jakob Heiss, Josef Teichmann, Hanna Wutte

In this paper, we consider one dimensional (shallow) ReLU neural networks in which weights are chosen randomly and only the terminal layer is trained. First, we mathematically show that for such networks L2-regularized r…

regression

Reducing the number of neurons of Deep ReLU Networks based on the current theory of Regularization

2021-01-01 · Jakob Heiss, Alexis Stockinger, Josef Teichmann

We introduce a new Reduction Algorithm which makes use of the properties of ReLU neurons to reduce significantly the number of neurons in a trained Deep Neural Network. This algorithm is based on the recent theory of imp…

A Mechanism of Implicit Regularization in Deep Learning

2019-09-25 · Masayoshi Kubo, Genki Sugiura, Kenta Shinzato, Momose Oyama

Despite a lot of theoretical efforts, very little is known about mechanisms of implicit regularization by which the low complexity contributes to generalization in deep learning. In particular, causality between the gene…

Deep LearningGeneralization Bounds

Implicit Regularization in ReLU Networks with the Square Loss

2020-12-09 · Gal Vardi, Ohad Shamir

Understanding the implicit regularization (or implicit bias) of gradient descent has recently been a very active research area. However, the implicit regularization in nonlinear neural networks is still poorly understood…

Support Vectors and Gradient Dynamics of Single-Neuron ReLU Networks

2022-02-11 · Sangmin Lee, Byeongsu Sim, Jong Chul Ye

Understanding implicit bias of gradient descent for generalization capability of ReLU networks has been an important research topic in machine learning research. Unfortunately, even for a single ReLU neuron trained with …