Publications

Found 50 results
Author Title Type [ Year(Desc)]
Filters: Author is Michael W. Mahoney  [Clear All Filters]
2016
Lawlor, D., Budavári T., & Mahoney M. W. (2016).  Mapping the Similarities of Spectra: Global and Locally-biased Approaches to SDSS Galaxy Data. The Astrophysical Journal.
Gittens, A., Devarakonda A., Racah E., Ringenburg M., Gerhardt L., Kottalam J., et al. (2016).  Matrix Factorization at Scale: a Comparison of Scientific Data Analytics in Spark and C+MPI Using Three Case Studies.
Gleich, D., & Mahoney M. W. (2016).  Mining Large graphs. Handbook of Big Data. 191-220.
Gittens, A., Kottalam J., Yang J., Ringenburg M. F., Chhugani J., Racah E., et al. (2016).  A multi-platform evaluation of the randomized CX low-rank matrix factorization in Spark. Proceedings of the 5th International Workshop on Parallel and Distributed Computing for Large Scale Machine Learning and Big Data Analytics.
Fountoulakis, K., Gleich D., & Mahoney M. W. (2016).  An optimization approach to locally-biased graph algorithms.
Shun, J., Roosta-Khorasani F., Fountoulakis K., & Mahoney M. W. (2016).  Parallel Local Graph Clustering. Proceedings of the VLDB Endowment. 9(12), 
Gallopoulos, E., Drineas P., Ipsen I., & Mahoney M. W. (2016).  RandNLA, Pythons, and the CUR for Your Data Problems: Reporting from G2S3 2015 in Delphi. SIAM News.
Drineas, P., & Mahoney M. W. (2016).  RandNLA: Randomized Numerical Linear Algebra. Communications of the ACM. 59, 80-90.
Veldt, N., Gleich D., & Mahoney M. W. (2016).  A Simple and Strongly-Local Flow-Based Method for Cut Improvement. Proceedings of the 33rd ICML Conference.
Mahoney, M. W., & Drineas P. (2016).  Structural properties underlying high-quality Randomized Numerical Linear Algebra algorithms. Handbook of Big Data. 137-154.
Roosta-Khorasani, F., & Mahoney M. W. (2016).  Sub-Sampled Newton Methods I: Globally Convergent Algorithms.
Roosta-Khorasani, F., & Mahoney M. W. (2016).  Sub-Sampled Newton Methods II: Local Convergence Rates.
Xu, P., Yang J., Roosta-Khorasani F., Re C., & Mahoney M. W. (2016).  Sub-sampled Newton Methods with Non-uniform Sampling. Proceedings of the 2016 NIPS Conference.
2017
Jing, L., Liu B., Choi J., Janin A., Bernd J., Mahoney M. W., et al. (2017).  DCAR: A Discriminative and Compact Audio Representation for Audio Processing. IEEE Transactions on Multimedia. PP(99), 
2018
Mahoney, M. W., Duchi J. C., & Gilbert A. C. (2018).  The Mathematics of Data. 25,
2019
Zhang, T.., Yao Z.., Gholami A.., Keutzer K.., Gonzalez J.., Biros G.., et al. (2019).  ANODEV2: A Coupled Neural ODE Evolution Framework. Proceedings of the 2019 NeurIPS Conference.
Derezinski, M.., & Mahoney M. W. (2019).  Distributed estimation of the inverse Hessian by determinantal averaging. Proceedings of the 2019 NeurIPS Conference.
Dong, Z.., Yao Z.., Gholami A.., Mahoney M. W., & Keutzer K.. (2019).  HAWQ: Hessian AWare Quantization of Neural Networks with Mixed-Precision. Proceedings of ICCV 2019.
Derezinski, M.., Clarkson K.. L., Mahoney M. W., & 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. W. (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. W. (2019).  Sub-Sampled Newton Methods. Mathematical Programming. 293-326.
Martin, C.. H., & Mahoney M. W. (2019).  Traditional and Heavy-Tailed Self Regularization in Neural Network Models. Proceeding of the 36th ICML Conference. 4284-4293.
2020
Martin, C.. H., & Mahoney M. W. (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.
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.

Pages