Preventing Gradient Attenuation in Lipschitz Constrained Convolutional Networks

3 November 2019

Joern-Henrik Jacobsen

ArXiv PDF HTML

Papers citing "Preventing Gradient Attenuation in Lipschitz Constrained Convolutional Networks"

32 / 32 papers shown

Title
Enhancing Certified Robustness via Block Reflector Orthogonal Layers and Logit Annealing Loss Bo-Han Lai Pin-Han Huang Bo-Han Kung Shang-Tse Chen 12 0 0 21 May 2025
Parseval Convolution Operators and Neural Networks Michael Unser Stanislas Ducotterd 25 3 0 19 Aug 2024
Detecting Brittle Decisions for Free: Leveraging Margin Consistency in Deep Robust Classifiers Jonas Ngnawé Sabyasachi Sahoo Y. Pequignot Frédéric Precioso Christian Gagné AAML 42 0 0 26 Jun 2024
Bridging The Gap between Low-rank and Orthogonal Adaptation via Householder Reflection Adaptation Shen Yuan Haotian Liu Hongteng Xu 44 2 0 24 May 2024
Graph Unitary Message Passing Haiquan Qiu Yatao Bian Quanming Yao 42 2 0 17 Mar 2024
A PAC-Bayesian Link Between Generalisation and Flat Minima Maxime Haddouche Paul Viallard Umut Simsekli Benjamin Guedj 45 3 0 13 Feb 2024
$Improve Robustness of Reinforcement Learning against Observation Perturbations via $l_\infty$ Lipschitz Policy Networks$ Improve Robustness of Reinforcement Learning against Observation Perturbations via $l_\infty$ Lipschitz Policy Networks Buqing Nie Jingtian Ji Yangqing Fu Yue Gao 48 4 0 14 Dec 2023
1-Lipschitz Neural Networks are more expressive with N-Activations Bernd Prach Christoph H. Lampert AAML FAtt 24 0 0 10 Nov 2023
LipSim: A Provably Robust Perceptual Similarity Metric Sara Ghazanfari Alexandre Araujo Prashanth Krishnamurthy Farshad Khorrami Siddharth Garg 46 5 0 27 Oct 2023
Function-Space Optimality of Neural Architectures with Multivariate Nonlinearities Rahul Parhi Michael Unser 49 5 0 05 Oct 2023
Certified Robust Models with Slack Control and Large Lipschitz Constants M. Losch David Stutz Bernt Schiele Mario Fritz 14 4 0 12 Sep 2023
Robust low-rank training via approximate orthonormal constraints Dayana Savostianova Emanuele Zangrando Gianluca Ceruti Francesco Tudisco 29 9 0 02 Jun 2023
A Unified Algebraic Perspective on Lipschitz Neural Networks Alexandre Araujo Aaron J. Havens Blaise Delattre A. Allauzen Bin Hu AAML 36 53 0 06 Mar 2023
Robust One-Class Classification with Signed Distance Function using 1-Lipschitz Neural Networks Louis Bethune Paul Novello Thibaut Boissin Guillaume Coiffier M. Serrurier Quentin Vincenot Andres Troya-Galvis 36 8 0 26 Jan 2023
Towards Practical Control of Singular Values of Convolutional Layers Alexandra Senderovich Ekaterina Bulatova Anton Obukhov M. Rakhuba AAML 19 9 0 24 Nov 2022
Improved techniques for deterministic l2 robustness Sahil Singla S. Feizi AAML 25 10 0 15 Nov 2022
Improving Lipschitz-Constrained Neural Networks by Learning Activation Functions Stanislas Ducotterd Alexis Goujon Pakshal Bohra Dimitris Perdios Sebastian Neumayer M. Unser 35 12 0 28 Oct 2022
Dynamical systems' based neural networks E. Celledoni Davide Murari B. Owren Carola-Bibiane Schönlieb Ferdia Sherry OOD 46 12 0 05 Oct 2022
Provably Adversarially Robust Nearest Prototype Classifiers Václav Voráček Matthias Hein AAML 20 11 0 14 Jul 2022
Towards Evading the Limits of Randomized Smoothing: A Theoretical Analysis Raphael Ettedgui Alexandre Araujo Rafael Pinot Y. Chevaleyre Jamal Atif AAML 34 3 0 03 Jun 2022
Approximation of Lipschitz Functions using Deep Spline Neural Networks Sebastian Neumayer Alexis Goujon Pakshal Bohra M. Unser 37 16 0 13 Apr 2022
projUNN: efficient method for training deep networks with unitary matrices B. Kiani Randall Balestriero Yann LeCun S. Lloyd 54 32 0 10 Mar 2022
On the Minimal Adversarial Perturbation for Deep Neural Networks with Provable Estimation Error Fabio Brau Giulio Rossolini Alessandro Biondi Giorgio Buttazzo AAML 36 7 0 04 Jan 2022
GraN-GAN: Piecewise Gradient Normalization for Generative Adversarial Networks Vineeth S. Bhaskara Tristan Aumentado-Armstrong Allan D. Jepson Alex Levinshtein GAN 43 5 0 04 Nov 2021
CC-Cert: A Probabilistic Approach to Certify General Robustness of Neural Networks Mikhail Aleksandrovich Pautov Nurislam Tursynbek Marina Munkhoeva Nikita Muravev Aleksandr Petiushko Ivan Oseledets AAML 52 16 0 22 Sep 2021
Existence, Stability and Scalability of Orthogonal Convolutional Neural Networks El Mehdi Achour Franccois Malgouyres Franck Mamalet 18 21 0 12 Aug 2021
Globally-Robust Neural Networks Klas Leino Zifan Wang Matt Fredrikson AAML OOD 80 126 0 16 Feb 2021
SoK: Certified Robustness for Deep Neural Networks Linyi Li Tao Xie Bo-wen Li AAML 33 128 0 09 Sep 2020
Deep Isometric Learning for Visual Recognition Haozhi Qi Chong You Xinyu Wang Yi Ma Jitendra Malik VLM 35 54 0 30 Jun 2020
The Convolution Exponential and Generalized Sylvester Flows Emiel Hoogeboom Victor Garcia Satorras Jakub M. Tomczak Max Welling 30 28 0 02 Jun 2020
Dynamical Isometry and a Mean Field Theory of CNNs: How to Train 10,000-Layer Vanilla Convolutional Neural Networks Lechao Xiao Yasaman Bahri Jascha Narain Sohl-Dickstein S. Schoenholz Jeffrey Pennington 244 350 0 14 Jun 2018
Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networks Guy Katz Clark W. Barrett D. Dill Kyle D. Julian Mykel Kochenderfer AAML 249 1,842 0 03 Feb 2017