paper-with-me

Papers

Depth-Width Tradeoffs in Approximating Natural Functions with Neural Networks

2016-10-31 · ICML 2017 8 · Itay Safran, Ohad Shamir

We provide several new depth-based separation results for feed-forward neural networks, proving that various types of simple and natural functions can be better approximated using deeper networks than shallower ones, even if the shallower networks are much larger. This includes indicators of balls and ellipses; non-linear functions which are radial with respect to the $L_1$ norm; and smooth non-linear functions. We also show that these gaps can be observed experimentally: Increasing the depth indeed allows better learning than increasing width, when training neural networks to learn an indicator of a unit ball.

📄 PDF Abstract BibTeX arXiv:1610.09887

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Expressivity of Neural Networks via Chaotic Itineraries beyond Sharkovsky's Theorem

2021-10-19 · Clayton Sanford, Vaggos Chatziafratis

Given a target function $f$, how large must a neural network be in order to approximate $f$? Recent works examine this basic question on neural network \textit{expressivity} from the lens of dynamical systems and provide…

Approximating Continuous Functions by ReLU Nets of Minimal Width

2017-10-31 · Boris Hanin, Mark Sellke

This article concerns the expressive power of depth in deep feed-forward neural nets with ReLU activations. Specifically, we answer the following question: for a fixed $d_{in}\geq 1,$ what is the minimal width $w$ so tha…

Universal approximation with complex-valued deep narrow neural networks

2023-05-26 · Paul Geuchen, Thomas Jahn, Hannes Matt

We study the universality of complex-valued neural networks with bounded widths and arbitrary depths. Under mild assumptions, we give a full description of those activation functions $\varrho:\mathbb{C}\to \mathbb{C}$ th…

How Many Neurons Does it Take to Approximate the Maximum?

2023-07-18 · Itay Safran, Daniel Reichman, Paul Valiant

We study the size of a neural network needed to approximate the maximum function over $d$ inputs, in the most basic setting of approximating with respect to the $L_2$ norm, for continuous distributions, for a network tha…

Approximating Matrix Functions with Deep Neural Networks and Transformers

2026-02-08 · Rahul Padmanabhan, Simone Brugiapaglia arxiv

Transformers have revolutionized natural language processing, but their use for numerical computation has received less attention. We study the approximation of matrix functions, which map scalar functions to matrices, u…