Skip to content
conftrace_

depth-width tradeoff

6 papers

Explore in graph

Co-occurring keywords · papers mentioning both

dynamical system (3) periodic point (2) approximation theory (2) approximation error (2) function approximation (2) chaotic itinerary (1) turing universality (1) periodic function (1) neural network (1) graph neural network (1)

Papers

The Median is Easier than it Looks: Approximation with a Constant-Depth, Linear-Width ReLU Network COLT 2026 Expressivity of Neural Networks via Chaotic Itineraries beyond Sharkovsky’s Theorem AISTATS 2022 Better depth-width trade-offs for neural networks through the lens of dynamical systems ICML 2020 Depth-Width Trade-offs for ReLU Networks via Sharkovsky's Theorem ICLR 2020 What graph neural networks cannot learn: depth vs width ICLR 2020 Depth-Width Tradeoffs in Approximating Natural Functions with Neural Networks ICML 2017