v1v2 (latest)

Complexity of Linear Regions in Deep Networks

25 January 2019

Papers citing "Complexity of Linear Regions in Deep Networks"

50 / 131 papers shown

Title
Data Augmentation Techniques to Reverse-Engineer Neural Network Weights from Input-Output Queries Alexander Beiser Flavio Martinelli W. Gerstner Johanni Brea 184 0 0 25 Nov 2025
TetraSDF: Precise Mesh Extraction with Multi-resolution Tetrahedral Grid Seonghun Oh Youngjung Uh Jin-Hwa Kim 132 0 0 20 Nov 2025
Topological Signatures of ReLU Neural Network Activation Patterns Vicente Bosca Tatum Rask Sunia Tanweer Andrew R. Tawfeek Branden Stone 84 0 0 14 Oct 2025
Designing ReLU Generative Networks to Enumerate Trees with a Given Tree Edit Distance Mamoona Ghafoor Tatsuya Akutsu 66 0 0 12 Oct 2025
Interlaced dynamic XCT reconstruction with spatio-temporal implicit neural representations Mathias Boulanger Ericmoore Jossou 84 0 0 09 Oct 2025
GLAI: GreenLightningAI for Accelerated Training through Knowledge Decoupling Jose I. Mestre Alberto Fernández-Hernández Cristian Pérez-Corral Manuel F. Dolz Jose Duato Enrique S. Quintana-Ortí 169 0 0 01 Oct 2025
Machine learning approach to single-shot multiparameter estimation for the non-linear Schrödinger equation Louis Rossignol Tangui Aladjidi Myrann Baker-Rasooli Quentin Glorieux 76 0 0 23 Sep 2025
Discrete Functional Geometry of ReLU Networks via ReLU Transition Graphs Sahil Rajesh Dhayalkar 150 0 0 03 Sep 2025
Fidelity Isn't Accuracy: When Linearly Decodable Functions Fail to Match the Ground Truth Jackson Eshbaugh FAtt 214 0 0 13 Jun 2025
Time to Spike? Understanding the Representational Power of Spiking Neural Networks in Discrete Time Duc Anh Nguyen Ernesto Araya Adalbert Fono Gitta Kutyniok 511 0 0 23 May 2025
Critical Points of Random Neural Networks Simmaco Di Lillo 280 1 0 22 May 2025
Fractal and Regular Geometry of Deep Neural Networks Simmaco Di Lillo Domenico Marinucci Michele Salvi Stefano Vigogna MDE AI4CE 215 2 0 08 Apr 2025
Beyond the Next Token: Towards Prompt-Robust Zero-Shot Classification via Efficient Multi-Token PredictionNorth American Chapter of the Association for Computational Linguistics (NAACL), 2025 Junlang Qian Zixiao Zhu Hanzhang Zhou Zijian Feng Zepeng Zhai K. Mao AAML VLM 323 0 0 04 Apr 2025
ReLU Networks as Random Functions: Their Distribution in Probability Space Shreyas Chaudhari J. M. F. Moura 258 0 0 28 Mar 2025
On Space Folds of ReLU Neural Networks Michal Lewandowski Hamid Eghbalzadeh Bernhard Heinzl Raphael Pisoni Bernhard A.Moser MLT 392 2 0 17 Feb 2025
Hamiltonian Monte Carlo on ReLU Neural Networks is InefficientNeural Information Processing Systems (NeurIPS), 2024 Vu C. Dinh L. Ho Cuong V Nguyen 136 2 0 29 Oct 2024
Get rich quick: exact solutions reveal how unbalanced initializations promote rapid feature learningNeural Information Processing Systems (NeurIPS), 2024 D. Kunin Allan Raventós Clémentine Dominé Feng Chen David Klindt Andrew M. Saxe Surya Ganguli MLT 323 25 0 10 Jun 2024
Growing Tiny Networks: Spotting Expressivity Bottlenecks and Fixing Them Optimally Manon Verbockhaven Sylvain Chevallier Guillaume Charpiat 183 7 0 30 May 2024
Spectral Truncation Kernels: Noncommutativity in $C^*$ -algebraic Kernel Machines Yuka Hashimoto Ayoub Hafid Masahiro Ikeda Hachem Kadri 401 2 0 28 May 2024
Spectral complexity of deep neural networksSIAM Journal on Mathematics of Data Science (SIMODS), 2024 Simmaco Di Lillo Domenico Marinucci Michele Salvi Stefano Vigogna BDL 428 2 0 15 May 2024
Graph is all you need? Lightweight data-agnostic neural architecture search without training Zhenhan Huang Tejaswini Pedapati Pin-Yu Chen Chunheng Jiang Jianxi Gao GNN 328 1 0 02 May 2024
Computing conservative probabilities of rare events with surrogates Nicolas Bousquet 213 0 0 26 Mar 2024
Analyzing Generalization in Policy Networks: A Case Study with the Double-Integrator SystemAAAI Conference on Artificial Intelligence (AAAI), 2023 Ruining Zhang H. Han Maolong Lv Qisong Yang Jian Cheng OffRL 223 4 0 16 Dec 2023
The Evolution of the Interplay Between Input Distributions and Linear Regions in Networks Xuan Qi Yi Wei 181 0 0 28 Oct 2023
Quantitative CLTs in Deep Neural NetworksProbability theory and related fields (PTRF), 2023 Stefano Favaro Boris Hanin Domenico Marinucci I. Nourdin G. Peccati BDL 623 25 0 12 Jul 2023
Zero-Shot Neural Architecture Search: Challenges, Solutions, and OpportunitiesIEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2023 Guihong Li Duc-Tuong Hoang Kartikeya Bhardwaj Ming Lin Zinan Lin R. Marculescu 353 36 0 05 Jul 2023
Why do CNNs excel at feature extraction? A mathematical explanation V. Nandakumar Arush Tagade Tongliang Liu FAtt 91 1 0 03 Jul 2023
Neural Polytopes Koji Hashimoto T. Naito Hisashi Naito 287 1 0 03 Jul 2023
Polyhedral Complex Extraction from ReLU Networks using Edge SubdivisionInternational Conference on Machine Learning (ICML), 2023 Arturs Berzins 184 9 0 12 Jun 2023
Deep ReLU Networks Have Surprisingly Simple Polytopes Fenglei Fan Wei Huang Xiang-yu Zhong Lecheng Ruan T. Zeng Huan Xiong Haiwei Yang 260 5 0 16 May 2023
SkelEx and BoundEx: Natural Visualization of ReLU Neural Networks Pawel Pukowski Haiping Lu 139 0 0 09 May 2023
When Deep Learning Meets Polyhedral Theory: A Survey Joey Huchette Gonzalo Muñoz Thiago Serra Calvin Tsay AI4CE 610 44 0 29 Apr 2023
The Power of Typed Affine Decision Structures: A Case StudyInternational Journal on Software Tools for Technology Transfer (STTT) (STTT), 2023 Gerrit Nolte Maximilian Schlüter Alnis Murtovi Bernhard Steffen AAML 133 2 0 28 Apr 2023
Expressivity of Shallow and Deep Neural Networks for Polynomial Approximation Itai Shapira 108 0 0 06 Mar 2023
SplineCam: Exact Visualization and Characterization of Deep Network Geometry and Decision BoundariesComputer Vision and Pattern Recognition (CVPR), 2023 Ahmed Imtiaz Humayun Randall Balestriero Guha Balakrishnan Richard Baraniuk 305 27 0 24 Feb 2023
On the Lipschitz Constant of Deep Networks and Double DescentBritish Machine Vision Conference (BMVC), 2023 Matteo Gamba Hossein Azizpour Mårten Björkman 514 10 0 28 Jan 2023
How does training shape the Riemannian geometry of neural network representations? Jacob A. Zavatone-Veth Sheng Yang Julian Rubinfien Cengiz Pehlevan MLT AI4CE 407 6 0 26 Jan 2023
Towards Rigorous Understanding of Neural Networks via Semantics-preserving TransformationsInternational Journal on Software Tools for Technology Transfer (STTT) (STTT), 2023 Maximilian Schlüter Gerrit Nolte Alnis Murtovi Bernhard Steffen 241 6 0 19 Jan 2023
Getting Away with More Network Pruning: From Sparsity to Geometry and Linear RegionsIntegration of AI and OR Techniques in Constraint Programming (CPAIOR), 2023 Junyang Cai Khai-Nguyen Nguyen Nishant Shrestha Aidan Good Ruisen Tu Xin Yu Shandian Zhe Thiago Serra MLT 268 11 0 19 Jan 2023
Expected Gradients of Maxout Networks and Consequences to Parameter InitializationInternational Conference on Machine Learning (ICML), 2023 Hanna Tseran Guido Montúfar ODL 162 1 0 17 Jan 2023
Understanding the Spectral Bias of Coordinate Based MLPs Via Training Dynamics J. Lazzari Xiuwen Liu 239 3 0 14 Jan 2023
Effects of Data Geometry in Early Deep LearningNeural Information Processing Systems (NeurIPS), 2022 Saket Tiwari George Konidaris 313 7 0 29 Dec 2022
Maximal Initial Learning Rates in Deep ReLU NetworksInternational Conference on Machine Learning (ICML), 2022 Gaurav M. Iyer Boris Hanin David Rolnick 248 14 0 14 Dec 2022
Interpreting Neural Networks through the Polytope Lens Sid Black Lee D. Sharkey Léo Grinsztajn Eric Winsor Daniel A. Braun ... Kip Parker Carlos Ramón Guevara Beren Millidge Gabriel Alfour Connor Leahy FAtt MILM 162 33 0 22 Nov 2022
Scalar Invariant Networks with Zero Bias Chuqin Geng Xiaojie Xu Haolin Ye X. Si 193 1 0 15 Nov 2022
Towards Reliable Neural SpecificationsInternational Conference on Machine Learning (ICML), 2022 Chuqin Geng Nham Le Xiaojie Xu Zhaoyue Wang A. Gurfinkel X. Si AAML 290 11 0 28 Oct 2022
Non-Linear Coordination GraphsNeural Information Processing Systems (NeurIPS), 2022 Yipeng Kang Tonghan Wang Xiao-Ren Wu Qianlan Yang Chongjie Zhang 157 10 0 26 Oct 2022
Understanding the Evolution of Linear Regions in Deep Reinforcement LearningNeural Information Processing Systems (NeurIPS), 2022 S. Cohan N. Kim David Rolnick M. van de Panne 147 7 0 24 Oct 2022
Deep Model ReassemblyNeural Information Processing Systems (NeurIPS), 2022 Xingyi Yang Zhou Daquan Songhua Liu Jingwen Ye Xinchao Wang MoMe 240 144 0 24 Oct 2022
When Expressivity Meets Trainability: Fewer than $n$ Neurons Can WorkNeural Information Processing Systems (NeurIPS), 2022 Jiawei Zhang Yushun Zhang Mingyi Hong Tian Ding Jianfeng Yao 287 10 0 21 Oct 2022