Prati
Michał Dereziński
Michał Dereziński
Assistant Professor at University of Michigan
Potvrđena adresa e-pošte na umich.edu - Početna stranica
Naslov
Citirano
Citirano
Godina
Exact expressions for double descent and implicit regularization via surrogate random design
M Dereziński, F Liang, MW Mahoney
Advances in Neural Information Processing Systems 33, 2020
592020
Determinantal point processes in randomized numerical linear algebra
M Derezinski, MW Mahoney
Notices of the American Mathematical Society 68 (1), 34-45, 2021
512021
Leveraged volume sampling for linear regression
M Derezinski, MKK Warmuth, DJ Hsu
Advances in Neural Information Processing Systems 31, 2018
512018
Unbiased estimates for linear regression via volume sampling
M Derezinski, MKK Warmuth
Advances in Neural Information Processing Systems 30, 2017
482017
Exact sampling of determinantal point processes with sublinear time preprocessing
M Derezinski, D Calandriello, M Valko
Advances in neural information processing systems 32, 2019
472019
Reverse iterative volume sampling for linear regression
M Dereziński, MK Warmuth
The Journal of Machine Learning Research 19 (1), 853-891, 2018
432018
Subsampling for ridge regression via regularized volume sampling
M Dereziński, MK Warmuth
arXiv preprint arXiv:1710.05110, 2017
262017
Improved guarantees and a multiple-descent curve for Column Subset Selection and the Nystrom method
M Derezinski, R Khanna, MW Mahoney
Advances in Neural Information Processing Systems 33, 4953-4964, 2020
242020
Fast determinantal point processes via distortion-free intermediate sampling
M Dereziński
Conference on Learning Theory, 1029-1049, 2019
242019
Debiasing distributed second order optimization with surrogate sketching and scaled regularization
M Derezinski, B Bartan, M Pilanci, MW Mahoney
Advances in Neural Information Processing Systems 33, 6684-6695, 2020
232020
Distributed estimation of the inverse hessian by determinantal averaging
M Derezinski, MW Mahoney
Advances in Neural Information Processing Systems 32, 2019
232019
Convergence analysis of block coordinate algorithms with determinantal sampling
M Mutny, M Derezinski, A Krause
International Conference on Artificial Intelligence and Statistics, 3110-3120, 2020
19*2020
Minimax experimental design: Bridging the gap between statistical and worst-case approaches to least-squares regression
M Derezinski, KL Clarkson, MK Warmuth, M Mahoney
Proceedings of Machine Learning Research vol 99, 1-20, 2019
182019
Correcting the bias in least squares regression with volume-rescaled sampling
M Derezinski, MK Warmuth, D Hsu
The 22nd International Conference on Artificial Intelligence and Statistics …, 2019
172019
Sampling from a k-DPP without looking at all items
D Calandriello, M Derezinski, M Valko
Advances in Neural Information Processing Systems 33, 6889-6899, 2020
162020
Precise expressions for random projections: Low-rank approximation and randomized Newton
M Derezinski, FT Liang, Z Liao, MW Mahoney
Advances in Neural Information Processing Systems 33, 18272-18283, 2020
152020
Bayesian experimental design using regularized determinantal point processes
M Derezinski, F Liang, M Mahoney
International Conference on Artificial Intelligence and Statistics, 3197-3207, 2020
142020
Isotropy and log-concave polynomials: Accelerated sampling and high-precision counting of matroid bases
N Anari, M Dereziński
2020 IEEE 61st Annual Symposium on Foundations of Computer Science (FOCS …, 2020
132020
Query complexity of least absolute deviation regression via robust uniform convergence
X Chen, M Derezinski
Conference on Learning Theory, 1144-1179, 2021
122021
Newton-LESS: Sparsification without trade-offs for the sketched newton update
M Derezinski, J Lacotte, M Pilanci, MW Mahoney
Advances in Neural Information Processing Systems 34, 2835-2847, 2021
112021
Sustav trenutno ne može provesti ovu radnju. Pokušajte ponovo kasnije.
Članci 1–20