Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Michael W. Mahoney

Compressing Deep ODE-Nets using Basis Function Expansions


Jun 21, 2021
Alejandro Queiruga, N. Benjamin Erichson, Liam Hodgkinson, Michael W. Mahoney


  Access Paper or Ask Questions

Post-mortem on a deep learning contest: a Simpson's paradox and the complementary roles of scale metrics versus shape metrics


Jun 01, 2021
Charles H. Martin, Michael W. Mahoney

* 23 pages; 9 figures; 6 tables 

  Access Paper or Ask Questions

MLPruning: A Multilevel Structured Pruning Framework for Transformer-based Models


May 30, 2021
Zhewei Yao, Linjian Ma, Sheng Shen, Kurt Keutzer, Michael W. Mahoney

* 20 pages, 4 figures, 9 tables 

  Access Paper or Ask Questions

ActNN: Reducing Training Memory Footprint via 2-Bit Activation Compressed Training


Apr 29, 2021
Jianfei Chen, Lianmin Zheng, Zhewei Yao, Dequan Wang, Ion Stoica, Michael W. Mahoney, Joseph E. Gonzalez


  Access Paper or Ask Questions

Q-ASR: Integer-only Zero-shot Quantization for Efficient Speech Recognition


Mar 31, 2021
Sehoon Kim, Amir Gholami, Zhewei Yao, Anirudda Nrusimha, Bohan Zhai, Tianren Gao, Michael W. Mahoney, Kurt Keutzer


  Access Paper or Ask Questions

A Survey of Quantization Methods for Efficient Neural Network Inference


Mar 25, 2021
Amir Gholami, Sehoon Kim, Zhen Dong, Zhewei Yao, Michael W. Mahoney, Kurt Keutzer

* Book Chapter: Low-Power Computer Vision: Improving the Efficiency of Artificial Intelligence 

  Access Paper or Ask Questions

Hessian Eigenspectra of More Realistic Nonlinear Models


Mar 17, 2021
Zhenyu Liao, Michael W. Mahoney

* Identical to v1, except for the inclusion of some additional references 

  Access Paper or Ask Questions

A Differential Geometry Perspective on Orthogonal Recurrent Models


Feb 18, 2021
Omri Azencot, N. Benjamin Erichson, Mirela Ben-Chen, Michael W. Mahoney


  Access Paper or Ask Questions

I-BERT: Integer-only BERT Quantization


Feb 11, 2021
Sehoon Kim, Amir Gholami, Zhewei Yao, Michael W. Mahoney, Kurt Keutzer


  Access Paper or Ask Questions

Noisy Recurrent Neural Networks


Feb 09, 2021
Soon Hoe Lim, N. Benjamin Erichson, Liam Hodgkinson, Michael W. Mahoney

* 38 pages 

  Access Paper or Ask Questions

Sparse sketches with small inversion bias


Nov 21, 2020
MichaƂ DereziƄski, Zhenyu Liao, Edgar Dobriban, Michael W. Mahoney


  Access Paper or Ask Questions

HAWQV3: Dyadic Neural Network Quantization


Nov 20, 2020
Zhewei Yao, Zhen Dong, Zhangcheng Zheng, Amir Gholami, Jiali Yu, Eric Tan, Leyuan Wang, Qijing Huang, Yida Wang, Michael W. Mahoney, Kurt Keutzer


  Access Paper or Ask Questions

A Statistical Framework for Low-bitwidth Training of Deep Neural Networks


Oct 27, 2020
Jianfei Chen, Yu Gai, Zhewei Yao, Michael W. Mahoney, Joseph E. Gonzalez

* 24 pages 

  Access Paper or Ask Questions

Fast Distributed Training of Deep Neural Networks: Dynamic Communication Thresholding for Model and Data Parallelism


Oct 18, 2020
Vipul Gupta, Dhruv Choudhary, Ping Tak Peter Tang, Xiaohan Wei, Xing Wang, Yuzhen Huang, Arun Kejariwal, Kannan Ramchandran, Michael W. Mahoney

* 17 pages, 8 figures 

  Access Paper or Ask Questions

MAF: Multimodal Alignment Framework for Weakly-Supervised Phrase Grounding


Oct 12, 2020
Qinxin Wang, Hao Tan, Sheng Shen, Michael W. Mahoney, Zhewei Yao


  Access Paper or Ask Questions

Sparse Quantized Spectral Clustering


Oct 03, 2020
Zhenyu Liao, Romain Couillet, Michael W. Mahoney


  Access Paper or Ask Questions

Benchmarking Semi-supervised Federated Learning


Aug 26, 2020
Zhengming Zhang, Zhewei Yao, Yaoqing Yang, Yujun Yan, Joseph E. Gonzalez, Michael W. Mahoney


  Access Paper or Ask Questions

Continuous-in-Depth Neural Networks


Aug 05, 2020
Alejandro F. Queiruga, N. Benjamin Erichson, Dane Taylor, Michael W. Mahoney


  Access Paper or Ask Questions

Noise-response Analysis for Rapid Detection of Backdoors in Deep Neural Networks


Jul 31, 2020
N. Benjamin Erichson, Dane Taylor, Qixuan Wu, Michael W. Mahoney


  Access Paper or Ask Questions

Adversarially-Trained Deep Nets Transfer Better


Jul 11, 2020
Francisco Utrera, Evan Kravitz, N. Benjamin Erichson, Rajiv Khanna, Michael W. Mahoney


  Access Paper or Ask Questions

Boundary thickness and robustness in learning models


Jul 09, 2020
Yaoqing Yang, Rajiv Khanna, Yaodong Yu, Amir Gholami, Kurt Keutzer, Joseph E. Gonzalez, Kannan Ramchandran, Michael W. Mahoney


  Access Paper or Ask Questions

Debiasing Distributed Second Order Optimization with Surrogate Sketching and Scaled Regularization


Jul 02, 2020
MichaƂ DereziƄski, Burak Bartan, Mert Pilanci, Michael W. Mahoney


  Access Paper or Ask Questions

Good linear classifiers are abundant in the interpolating regime


Jun 22, 2020
Ryan Theisen, Jason M. Klusowski, Michael W. Mahoney


  Access Paper or Ask Questions

Lipschitz Recurrent Neural Networks


Jun 22, 2020
N. Benjamin Erichson, Omri Azencot, Alejandro Queiruga, Michael W. Mahoney


  Access Paper or Ask Questions

Precise expressions for random projections: Low-rank approximation and randomized Newton


Jun 18, 2020
MichaƂ DereziƄski, Feynman Liang, Zhenyu Liao, Michael W. Mahoney


  Access Paper or Ask Questions

Multiplicative noise and heavy tails in stochastic optimization


Jun 11, 2020
Liam Hodgkinson, Michael W. Mahoney

* 30 pages, 7 figures 

  Access Paper or Ask Questions

A random matrix analysis of random Fourier features: beyond the Gaussian kernel, a precise phase transition, and the corresponding double descent


Jun 09, 2020
Zhenyu Liao, Romain Couillet, Michael W. Mahoney


  Access Paper or Ask Questions

ADAHESSIAN: An Adaptive Second Order Optimizer for Machine Learning


Jun 01, 2020
Zhewei Yao, Amir Gholami, Sheng Shen, Kurt Keutzer, Michael W. Mahoney


  Access Paper or Ask Questions