Revealing the Structure of Deep Neural Networks via Convex Duality

22 February 2020

Papers citing "Revealing the Structure of Deep Neural Networks via Convex Duality"

21 / 21 papers shown

Title
Linguistic Collapse: Neural Collapse in (Large) Language Models Robert Wu Vardan Papyan 48 12 0 28 May 2024
Analyzing Neural Network-Based Generative Diffusion Models through Convex Optimization Fangzhao Zhang Mert Pilanci DiffM 51 3 0 03 Feb 2024
ReLU Neural Networks with Linear Layers are Biased Towards Single- and Multi-Index Models Suzanna Parkinson Greg Ongie Rebecca Willett 68 6 0 24 May 2023
When Deep Learning Meets Polyhedral Theory: A Survey Joey Huchette Gonzalo Muñoz Thiago Serra Calvin Tsay AI4CE 94 32 0 29 Apr 2023
Perturbation Analysis of Neural Collapse Tom Tirer Haoxiang Huang Jonathan Niles-Weed AAML 46 24 0 29 Oct 2022
Are All Losses Created Equal: A Neural Collapse Perspective Jinxin Zhou Chong You Xiao Li Kangning Liu Sheng Liu Qing Qu Zhihui Zhu 36 59 0 04 Oct 2022
Improving Self-Supervised Learning by Characterizing Idealized Representations Yann Dubois Tatsunori Hashimoto Stefano Ermon Percy Liang SSL 83 40 0 13 Sep 2022
Neural Collapse: A Review on Modelling Principles and Generalization Vignesh Kothapalli 25 74 0 08 Jun 2022
On the Effective Number of Linear Regions in Shallow Univariate ReLU Networks: Convergence Guarantees and Implicit Bias Itay Safran Gal Vardi Jason D. Lee MLT 59 23 0 18 May 2022
Unraveling Attention via Convex Duality: Analysis and Interpretations of Vision Transformers Arda Sahiner Tolga Ergen Batu Mehmet Ozturkler John M. Pauly Morteza Mardani Mert Pilanci 40 33 0 17 May 2022
On the Optimization Landscape of Neural Collapse under MSE Loss: Global Optimality with Unconstrained Features Jinxin Zhou Xiao Li Tian Ding Chong You Qing Qu Zhihui Zhu 30 99 0 02 Mar 2022
Fast Convex Optimization for Two-Layer ReLU Networks: Equivalent Model Classes and Cone Decompositions Aaron Mishkin Arda Sahiner Mert Pilanci OffRL 77 30 0 02 Feb 2022
Path Regularization: A Convexity and Sparsity Inducing Regularization for Parallel ReLU Networks Tolga Ergen Mert Pilanci 32 16 0 18 Oct 2021
The Convex Geometry of Backpropagation: Neural Network Gradient Flows Converge to Extreme Points of the Dual Convex Program Yifei Wang Mert Pilanci MLT MDE 55 11 0 13 Oct 2021
Parallel Deep Neural Networks Have Zero Duality Gap Yifei Wang Tolga Ergen Mert Pilanci 79 10 0 13 Oct 2021
On Margin Maximization in Linear and ReLU Networks Gal Vardi Ohad Shamir Nathan Srebro 52 28 0 06 Oct 2021
A Geometric Analysis of Neural Collapse with Unconstrained Features Zhihui Zhu Tianyu Ding Jinxin Zhou Xiao Li Chong You Jeremias Sulam Qing Qu 30 194 0 06 May 2021
Adaptive and Oblivious Randomized Subspace Methods for High-Dimensional Optimization: Sharp Analysis and Lower Bounds Jonathan Lacotte Mert Pilanci 20 11 0 13 Dec 2020
Nonparametric Learning of Two-Layer ReLU Residual Units Zhunxuan Wang Linyun He Chunchuan Lyu Shay B. Cohen MLT OffRL 33 1 0 17 Aug 2020
Convex Geometry and Duality of Over-parameterized Neural Networks Tolga Ergen Mert Pilanci MLT 42 54 0 25 Feb 2020
Neural Networks are Convex Regularizers: Exact Polynomial-time Convex Optimization Formulations for Two-layer Networks Mert Pilanci Tolga Ergen 26 116 0 24 Feb 2020