The inductive bias of ReLU networks on orthogonally separable data
We study the inductive bias of two-layer ReLU networks trained by gradient flow. We identify a class of easy-to-learn (`orthogonally separable') datasets, and characterise the solution that ReLU networks trained on such datasets converge to. Irrespective of network width, the solution turns out to be a combination of two max-margin classifiers: one corresponding to the positive data subset and one corresponding to the negative data subset. The proof is based on the recently introduced concept of extremal sectors, for which we prove a number of properties in the context of orthogonal separability. In particular, we prove stationarity of activation patterns from some time $T$ onwards, which enables a reduction of the ReLU network to an ensemble of linear subnetworks.
Code (0)
등록된 구현이 없습니다.
Tasks
Inductive BiasMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Neural Collapse under Gradient Flow on Shallow ReLU Networks for Orthogonally Separable Data
Among many mysteries behind the success of deep networks lies the exceptional discriminative power of their learned representations as manifested by the intriguing Neural Collapse (NC) phenomenon, where simple feature st…
Do We Always Need the Simplicity Bias? Looking for Optimal Inductive Biases in the Wild
Neural architectures tend to fit their data with relatively simple functions. This "simplicity bias" is widely regarded as key to their success. This paper explores the limits of this principle. Building on recent findin…
image-classificationImage ClassificationAdversarial Reprogramming Revisited
Adversarial reprogramming, introduced by Elsayed, Goodfellow, and Sohl-Dickstein, seeks to repurpose a neural network to perform a different task, by manipulating its input without modifying its weights. We prove that tw…
Entrywise application of non-linear functions on orthogonally invariant matrices
In this article, we investigate how the entrywise application of a non-linear function to symmetric orthogonally invariant random matrix ensembles alters the spectral distribution. We treat also the multivariate case whe…
Neural Networks Fail to Learn Periodic Functions and How to Fix It
Previous literature offers limited clues on how to learn a periodic function using modern neural networks. We start with a study of the extrapolation properties of neural networks; we prove and demonstrate experimentally…
Inductive Bias