Deep Equilibrium Models are Almost Equivalent to Not-so-deep Explicit Models for High-dimensional Gaussian Mixtures

5 February 2024

Papers citing "Deep Equilibrium Models are Almost Equivalent to Not-so-deep Explicit Models for High-dimensional Gaussian Mixtures"

7 / 7 papers shown

Title
DDEQs: Distributional Deep Equilibrium Models through Wasserstein Gradient Flows Jonathan Geuter Clément Bonet Anna Korba David Alvarez-Melis 61 0 0 03 Mar 2025
Understanding Representation of Deep Equilibrium Models from Neural Collapse Perspective Haixiang Sun Ye Shi 42 0 0 30 Oct 2024
IGNN-Solver: A Graph Neural Solver for Implicit Graph Neural Networks Junchao Lin Zenan Ling Zhanbo Feng Feng Zhou Jingwen Xu Feng Zhou Tianqi Hou Zhenyu Liao Robert C. Qiu GNN AI4CE 54 0 0 11 Oct 2024
On Dissipativity of Cross-Entropy Loss in Training ResNets Jens Püttschneider T. Faulwasser 35 0 0 29 May 2024
"Lossless" Compression of Deep Neural Networks: A High-dimensional Neural Tangent Kernel Approach Lingyu Gu Yongqiang Du Yuan Zhang Di Xie Shiliang Pu Robert C. Qiu Zhenyu Liao 44 6 0 01 Mar 2024
Gradient Descent Optimizes Infinite-Depth ReLU Implicit Networks with Linear Widths Tianxiang Gao Hongyang Gao MLT 35 5 0 16 May 2022
Random matrices in service of ML footprint: ternary random features with no performance loss Hafiz Tiomoko Ali Zhenyu Liao Romain Couillet 44 7 0 05 Oct 2021