| Risk bounds for high-dimensional ridge function combinations including neural networks JM Klusowski, AR Barron arXiv preprint arXiv:1607.01434, 2016 | 41 | 2016 |
| Approximation by Combinations of ReLU and Squared ReLU Ridge Functions WithandControls JM Klusowski, AR Barron IEEE Transactions on Information Theory 64 (12), 7649-7656, 2018 | 33 | 2018 |
| Approximation and estimation for high-dimensional deep learning networks AR Barron, JM Klusowski arXiv preprint arXiv:1809.03090, 2018 | 32 | 2018 |
| Algorithmic analysis and statistical estimation of slope via approximate message passing Z Bu, J Klusowski, C Rush, W Su arXiv preprint arXiv:1907.07502, 2019 | 17 | 2019 |
| Statistical guarantees for estimating the centers of a two-component Gaussian mixture by EM JM Klusowski, WD Brinda arXiv preprint arXiv:1608.02280, 2016 | 13 | 2016 |
| Counting motifs with graph sampling JM Klusowski, Y Wu Conference On Learning Theory, 1966-2011, 2018 | 12 | 2018 |
| Uniform approximation by neural networks activated by first and second order ridge splines JM Klusowski, AR Barron arXiv preprint arXiv:1607.07819, 2016 | 12 | 2016 |
| Estimating the coefficients of a mixture of two linear regressions by expectation maximization JM Klusowski, D Yang, WD Brinda IEEE Transactions on Information Theory 65 (6), 3515-3524, 2019 | 11 | 2019 |
| Complete analysis of a random forest model JM Klusowski arXiv preprint arXiv:1805.02587, 2018 | 11 | 2018 |
| Minimax lower bounds for ridge combinations including neural nets JM Klusowski, AR Barron 2017 IEEE International Symposium on Information Theory (ISIT), 1376-1380, 2017 | 11 | 2017 |
| Complexity, statistical risk, and metric entropy of deep nets using total path variation AR Barron, JM Klusowski arXiv preprint arXiv:1902.00800, 2019 | 10 | 2019 |
| Estimating the number of connected components in a graph via subgraph sampling JM Klusowski, Y Wu arXiv preprint arXiv:1801.04339, 2018 | 9 | 2018 |
| Estimating the coefficients of a mixture of two linear regressions by expectation maximization JM Klusowski, D Yang, WD Brinda arXiv preprint arXiv:1704.08231, 2017 | 5 | 2017 |
| Sharp analysis of a simple model for random forests JM Klusowski arXiv preprint arXiv:1805.02587, 2018 | 4 | 2018 |
| Finite-sample risk bounds for maximum likelihood estimation with arbitrary penalties WD Brinda, JM Klusowski IEEE Transactions on Information Theory 64 (4), 2727-2741, 2018 | 4 | 2018 |
| Analyzing CART JM Klusowski arXiv preprint arXiv:1906.10086, 2019 | 3 | 2019 |
| Estimation of convex supports from noisy measurements VE Brunel, JM Klusowski, D Yang arXiv preprint arXiv:1804.09879, 2018 | 2 | 2018 |
| Lecture notes on information theory G Ajjanagadde, A Makur, J Klusowski, S Xu | 2 | 2017 |
| Good linear classifiers are abundant in the interpolating regime R Theisen, JM Klusowski, MW Mahoney arXiv preprint arXiv:2006.12625, 2020 | 1 | 2020 |
| Global Capacity Measures for Deep ReLU Networks via Path Sampling R Theisen, JM Klusowski, H Wang, NS Keskar, C Xiong, R Socher arXiv preprint arXiv:1910.10245, 2019 | 1 | 2019 |
Andrew R BarronProfessor of Statistics, Yale UniversityVerified email at yale.edu
