Lossless Compression of Deep Neural Networks

1 January 2020

Papers citing "Lossless Compression of Deep Neural Networks"

40 / 40 papers shown

Title
Tightening convex relaxations of trained neural networks: a unified approach for convex and S-shaped activations Pablo Carrasco Gonzalo Muñoz 59 2 0 30 Oct 2024
Free Lunch in the Forest: Functionally-Identical Pruning of Boosted Tree Ensembles Youssouf Emine Alexandre Forel Idriss Malek Thibaut Vidal 30 0 0 28 Aug 2024
Optimization Over Trained Neural Networks: Taking a Relaxing Walk Jiatai Tong Junyang Cai Thiago Serra 60 6 0 07 Jan 2024
Computational Tradeoffs of Optimization-Based Bound Tightening in ReLU Networks Fabian Badilla Marcos Goycoolea Gonzalo Muñoz Thiago Serra 57 7 0 27 Dec 2023
FedSZ: Leveraging Error-Bounded Lossy Compression for Federated Learning Communications Grant Wilkins Sheng Di Jon C. Calhoun Zilinghan Li Kibaek Kim Robert Underwood Richard Mortier Franck Cappello FedML 32 2 0 20 Dec 2023
Mixed-Integer Optimisation of Graph Neural Networks for Computer-Aided Molecular Design Tom McDonald Calvin Tsay Artur M. Schweidtmann Neil Yorke-Smith 58 14 0 02 Dec 2023
Proximity to Losslessly Compressible Parameters Matthew Farrugia-Roberts 17 0 0 05 Jun 2023
Learning Prescriptive ReLU Networks Wei-Ju Sun Asterios Tsiourvas 14 2 0 01 Jun 2023
When Deep Learning Meets Polyhedral Theory: A Survey Joey Huchette Gonzalo Muñoz Thiago Serra Calvin Tsay AI4CE 91 32 0 29 Apr 2023
Model-based feature selection for neural networks: A mixed-integer programming approach Shudian Zhao Calvin Tsay Jan Kronqvist 19 5 0 20 Feb 2023
Getting Away with More Network Pruning: From Sparsity to Geometry and Linear Regions Junyang Cai Khai-Nguyen Nguyen Nishant Shrestha Aidan Good Ruisen Tu Xin Yu Shandian Zhe Thiago Serra MLT 14 7 0 19 Jan 2023
The Effect of Data Dimensionality on Neural Network Prunability Zachary Ankner Alex Renda Gintare Karolina Dziugaite Jonathan Frankle Tian Jin 11 5 0 01 Dec 2022
Pruning's Effect on Generalization Through the Lens of Training and Regularization Tian Jin Michael Carbin Daniel M. Roy Jonathan Frankle Gintare Karolina Dziugaite 13 27 0 25 Oct 2022
Towards Global Neural Network Abstractions with Locally-Exact Reconstruction Edoardo Manino I. Bessa Lucas C. Cordeiro 17 1 0 21 Oct 2022
Quiver neural networks I. Ganev Robin G. Walters 12 4 0 26 Jul 2022
Support Vector Machines with the Hard-Margin Loss: Optimal Training via Combinatorial Benders' Cuts Ítalo Santana Breno Serrano Maximilian Schiffer Thibaut Vidal 19 3 0 15 Jul 2022
Deep Neural Networks pruning via the Structured Perspective Regularization M. Cacciola A. Frangioni Xinlin Li Andrea Lodi 3DPC 18 5 0 28 Jun 2022
Recall Distortion in Neural Network Pruning and the Undecayed Pruning Algorithm Aidan Good Jia-Huei Lin Hannah Sieg Mikey Ferguson Xin Yu Shandian Zhe J. Wieczorek Thiago Serra 14 11 0 07 Jun 2022
Optimizing Objective Functions from Trained ReLU Neural Networks via Sampling G. Perakis Asterios Tsiourvas 12 11 0 27 May 2022
The Combinatorial Brain Surgeon: Pruning Weights That Cancel One Another in Neural Networks Xin Yu Thiago Serra Srikumar Ramalingam Shandian Zhe 11 48 0 09 Mar 2022
P-split formulations: A class of intermediate formulations between big-M and convex hull for disjunctive constraints Jan Kronqvist Ruth Misener Calvin Tsay 46 7 0 10 Feb 2022
OMLT: Optimization & Machine Learning Toolkit Francesco Ceccon Jordan Jalving Joshua Haddad Alexander Thebelt Calvin Tsay C. Laird Ruth Misener 25 67 0 04 Feb 2022
Training Thinner and Deeper Neural Networks: Jumpstart Regularization Carles Roger Riera Molina Camilo Rey Thiago Serra Eloi Puertas O. Pujol 22 4 0 30 Jan 2022
Parameter identifiability of a deep feedforward ReLU neural network Joachim Bona-Pellissier François Bachoc François Malgouyres 20 14 0 24 Dec 2021
Optimizing over an ensemble of neural networks Keliang Wang Leonardo Lozano C. Cardonha David Bergman UQCV 15 1 0 13 Dec 2021
On the Impact of Stable Ranks in Deep Nets B. Georgiev L. Franken Mayukh Mukherjee Georgios Arvanitidis 13 3 0 05 Oct 2021
Universal approximation and model compression for radial neural networks I. Ganev Twan van Laarhoven Robin G. Walters 9 8 0 06 Jul 2021
On the Expected Complexity of Maxout Networks Hanna Tseran Guido Montúfar 17 11 0 01 Jul 2021
Towards Lower Bounds on the Depth of ReLU Neural Networks Christoph Hertrich A. Basu M. D. Summa M. Skutella 29 41 0 31 May 2021
Scaling Up Exact Neural Network Compression by ReLU Stability Thiago Serra Xin Yu Abhinav Kumar Srikumar Ramalingam 8 24 0 15 Feb 2021
Partition-based formulations for mixed-integer optimization of trained ReLU neural networks Calvin Tsay Jan Kronqvist Alexander Thebelt Ruth Misener 17 68 0 08 Feb 2021
Between steps: Intermediate relaxations between big-M and convex hull formulations Jan Kronqvist Ruth Misener Calvin Tsay 13 12 0 29 Jan 2021
Unwrapping The Black Box of Deep ReLU Networks: Interpretability, Diagnostics, and Simplification Agus Sudjianto William Knauth Rahul Singh Zebin Yang Aijun Zhang FAtt 30 42 0 08 Nov 2020
Optimal training of integer-valued neural networks with mixed integer programming Tómas Thorbjarnarson Neil Yorke-Smith 11 9 0 08 Sep 2020
Lossless Compression of Structured Convolutional Models via Lifting Gustav Sourek F. Železný Ondrej Kuzelka 16 12 0 13 Jul 2020
Combining Reinforcement Learning and Constraint Programming for Combinatorial Optimization Quentin Cappart Thierry Moisan Louis-Martin Rousseau Isabeau Prémont-Schwarz A. Ciré 13 138 0 02 Jun 2020
Identifying Critical Neurons in ANN Architectures using Mixed Integer Programming M. Elaraby Guy Wolf Margarida Carvalho 13 5 0 17 Feb 2020
CAQL: Continuous Action Q-Learning Moonkyung Ryu Yinlam Chow Ross Anderson Christian Tjandraatmadja Craig Boutilier 191 42 0 26 Sep 2019
Principled Deep Neural Network Training through Linear Programming D. Bienstock Gonzalo Muñoz S. Pokutta 11 24 0 07 Oct 2018
Benefits of depth in neural networks Matus Telgarsky 123 600 0 14 Feb 2016