paper-with-me

홈 › Papers

The inductive bias of ReLU networks on orthogonally separable data

2021-01-01 · ICLR 2021 1 · Mary Phuong, Christoph H Lampert

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.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Inductive Bias

Methods 이 논문이 사용한 방법론

ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…

Similar Papers 제목 키워드 기반

Neural Collapse under Gradient Flow on Shallow ReLU Networks for Orthogonally Separable Data

2025-10-24 · Hancheng Min, Zhihui Zhu, René Vidal arxiv

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

2025-03-13 · CVPR 2025 1 · Damien Teney, Liangze Jiang, Florin Gogianu, Ehsan Abbasnejad

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 Classification

Adversarial Reprogramming Revisited

2022-06-07 · Matthias Englert, Ranko Lazic

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

2024-12-09 · Roland Speicher, Alexander Wendel

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

2020-06-15 · NeurIPS 2020 12 · Liu Ziyin, Tilman Hartwig, Masahito Ueda

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