Lower bounds over Boolean inputs for deep neural networks with ReLU
gates

v1v2 (latest)

Lower bounds over Boolean inputs for deep neural networks with ReLU gates

8 November 2017

Anirbit Mukherjee

ArXiv (abs)PDF HTML

Papers citing "Lower bounds over Boolean inputs for deep neural networks with ReLU gates"

9 / 9 papers shown

Title
Better Neural Network Expressivity: Subdividing the Simplex Egor Bakaev Florestan Brunck Christoph Hertrich Jack Stade Amir Yehudayoff 72 0 0 20 May 2025
Neural Networks and (Virtual) Extended Formulations Christoph Hertrich Georg Loho 134 3 0 05 Nov 2024
Transformers Learn Shortcuts to Automata Bingbin Liu Jordan T. Ash Surbhi Goel A. Krishnamurthy Cyril Zhang OffRL LRM 159 178 0 19 Oct 2022
$Training Fully Connected Neural Networks is $\exists\mathbb{R}$-Complete$ Training Fully Connected Neural Networks is $\exists\mathbb{R}$ -Complete Daniel Bertschinger Christoph Hertrich Paul Jungeblut Tillmann Miltzow Simon Weber OffRL 115 30 0 04 Apr 2022
VC dimension of partially quantized neural networks in the overparametrized regime Yutong Wang Clayton D. Scott 76 1 0 06 Oct 2021
Size and Depth Separation in Approximating Benign Functions with Neural Networks Gal Vardi Daniel Reichman T. Pitassi Ohad Shamir 76 7 0 30 Jan 2021
Provably Good Solutions to the Knapsack Problem via Neural Networks of Bounded Size Christoph Hertrich M. Skutella 99 22 0 28 May 2020
Learning One-hidden-layer ReLU Networks via Gradient Descent Xiao Zhang Yaodong Yu Lingxiao Wang Quanquan Gu MLT 129 135 0 20 Jun 2018
Limits on representing Boolean functions by linear combinations of simple functions: thresholds, ReLUs, and low-degree polynomials Richard Ryan Williams 60 27 0 26 Feb 2018