Publications

Found 73 results
Author Title Type [ Year(Desc)]
Filters: Author is Michael W. Mahoney  [Clear All Filters]
2019
Derezinski, M.., Clarkson K.. L., Mahoney M., & Warmuth M.. K. (2019).  Minimax experimental design: Bridging the gap between statistical and worst-case approaches to least squares regression. Proceedings of 2019 COLT.
Martin, C.. H., & Mahoney M. (2019).  Statistical Mechanics Methods for Discovering Knowledge from Modern Production Quality Neural Networks. Proceedings of the 25th Annual SIGKDD. 3239-3240.
Roosta-Khorasani, F.., & Mahoney M. (2019).  Sub-Sampled Newton Methods. Mathematical Programming. 293-326.
Martin, C.. H., & Mahoney M. (2019).  Traditional and Heavy-Tailed Self Regularization in Neural Network Models. Proceeding of the 36th ICML Conference. 4284-4293.
Yao, Z.., Gholami A.., Xu P.., Keutzer K.., & Mahoney M. (2019).  Trust Region Based Adversarial Attack on Neural Networks. Proceedings of the 32nd CVPR Conference. 11350-11359.
2020
Martin, C.. H., & Mahoney M. (2020).  Heavy-Tailed Universality Predicts Trends in Test Accuracies for Very Large Pre-Trained Deep Neural Networks. Proceedings of 2020 SDM Conference.
Ma, L.., Montague G.., Ye J.., Yao Z.., Gholami A.., Keutzer K.., et al. (2020).  Inefficiency of K-FAC for Large Batch Size Training. Proceedings of the AAAI-20 Conference.
Hodgkinson, L., & Mahoney M. (2020).  Multiplicative Noise and Heavy Tails in Stochastic Optimization.
Shen, S.., Dong Z.., Ye J.., Ma L.., Yao Z.., Gholami A.., et al. (2020).  Q-BERT: Hessian Based Ultra Low Precision Quantization of BERT. Proceedings of the AAAI-20 Conference.
N. Erichson, B., Mathelin L., Yao Z., Bruntonq S. L., Mahoney M., & J. Kutz N. (2020).  Shallow neural networks for fluid flow reconstruction with limited sensors. Proceedings of the Royal Society A. 476(2238), 
2021
Chen, J., Zheng L., Yao Z., Wang D., Stoica I., Mahoney M., et al. (2021).  ActNN: Reducing Training Memory Footprint via 2-Bit Activation Compressed Training.
Utrera, F., Kravitz E., N. Erichson B., Khanna R., & Mahoney M. (2021).  Adversarially-Trained Deep Nets Transfer Better: Illustration on Image Classification. International Conference on Learning Representations.
Krishnapriyan, A. S., Gholami A., Zhe S., Kirby R. M., & Mahoney M. W. (2021).  Characterizing Possible Failure Modes in Physics-Informed Neural Networks. NeurIPS.
Yao, Z., Dong Z., Zheng Z., Gholami A., Yu J., Tan E., et al. (2021).  HAWQV3: Dyadic Neural Network Quantization.
Kim, S., Gholami A., Yao Z., Mahoney M., & Keutzer K. (2021).  I-BERT: Integer-only BERT Quantization.
N. Erichson, B., Azencot O., Queiruga A., Hodgkinson L., & Mahoney M. (2021).  Lipschitz recurrent neural networks. International Conference on Learning Representations.
N. Erichson, B., Taylor D., Wu Q., & Mahoney M. (2021).  Noise-Response Analysis of Deep Neural Networks Quantifies Robustness and Fingerprints Structural Malware. Proceedings of the 2021 SIAM International Conference on Data Mining (SDM). 100-108.
Lim, S. Hoe, N. Erichson B., Hodgkinson L., & Mahoney M. (2021).  Noisy Recurrent Neural Networks. Advances in Neural Information Processing Systems Conference. 34,
2022
Kwon, W., Kim S., Mahoney M. W., Hassoun J., Keutzer K., & Gholami A. (2022).  A Fast Post-Training Pruning Framework for Transformers. NeurIPS.
Eshragh, A., Roosta F., Nazari A., & Mahoney M. (2022).  LSAR: Efficient Leverage Score Sampling Algorithm for the Analysis of Big Time Series Data. Journal of Machine Learning Research. 23, 1-36.
N. Erichson, B., Lim S. Hoe, Utrera F., Xu W., Cao Z., & Mahoney M. (2022).  NoisyMix: Boosting Robustness by Combining Data Augmentations, Stability Training, and Noise Injections. arXiv.
Chasins, S., Cheung A., Crooks N., Ghodsi A., Goldberg K., Gonzalez J. E., et al. (2022).  The Sky Above the Clouds: A Berkeley View on the Future of Cloud Computing. arxiv.org.
Kim, S., Gholami A., Shaw A., Lee N., Mangalam K., Malik J., et al. (2022).  Squeezeformer: An Efficient Transformer for Automatic Speech Recognition. NeurIPS.

Pages