The Convex Geometry of Backpropagation: Neural Network Gradient Flows Converge to Extreme Points of the Dual Convex Program

13 October 2021

Papers citing "The Convex Geometry of Backpropagation: Neural Network Gradient Flows Converge to Extreme Points of the Dual Convex Program"

8 / 8 papers shown

Title
Analyzing Neural Network-Based Generative Diffusion Models through Convex Optimization Fangzhao Zhang Mert Pilanci DiffM 23 3 0 03 Feb 2024
From Complexity to Clarity: Analytical Expressions of Deep Neural Network Weights via Clifford's Geometric Algebra and Convexity Mert Pilanci 8 2 0 28 Sep 2023
Early Neuron Alignment in Two-layer ReLU Networks with Small Initialization Hancheng Min Enrique Mallada René Vidal MLT 15 19 0 24 Jul 2023
Learning a Neuron by a Shallow ReLU Network: Dynamics and Implicit Bias for Correlated Inputs D. Chistikov Matthias Englert R. Lazic MLT 22 12 0 10 Jun 2023
Convex Dual Theory Analysis of Two-Layer Convolutional Neural Networks with Soft-Thresholding Chunyan Xiong Meng Lu Xiaotong Yu JIAN-PENG Cao Zhong Chen D. Guo X. Qu MLT 18 0 0 14 Apr 2023
Adversarial Reprogramming Revisited Matthias Englert R. Lazic AAML 8 8 0 07 Jun 2022
Gradient flow dynamics of shallow ReLU networks for square loss and orthogonal inputs Etienne Boursier Loucas Pillaud-Vivien Nicolas Flammarion ODL 11 58 0 02 Jun 2022
A Local Convergence Theory for Mildly Over-Parameterized Two-Layer Neural Network Mo Zhou Rong Ge Chi Jin 64 44 0 04 Feb 2021