| On convergence and stability of gans N Kodali, J Abernethy, J Hays, Z Kira arXiv preprint arXiv:1705.07215, 2017 | 957* | 2017 |
| Competing in the dark: An efficient algorithm for bandit linear optimization JD Abernethy, E Hazan, A Rakhlin Conference on Learning Theory, 2009 | 470 | 2009 |
| A new approach to collaborative filtering: Operator estimation with spectral regularization. J Abernethy, F Bach, T Evgeniou, JP Vert Journal of Machine Learning Research 10 (3), 2009 | 321 | 2009 |
| Dynamic online pricing with incomplete information using multiarmed bandit experiments K Misra, EM Schwartz, J Abernethy Marketing Science 38 (2), 226-252, 2019 | 293 | 2019 |
| Optimal strategies and minimax lower bounds for online convex games J Abernethy, PL Bartlett, A Rakhlin, A Tewari | 221 | 2008 |
| Blackwell approachability and no-regret learning are equivalent J Abernethy, PL Bartlett, E Hazan Proceedings of the 24th Annual Conference on Learning Theory, 27-46, 2011 | 167 | 2011 |
| Efficient market making via convex optimization, and a connection to online learning J Abernethy, Y Chen, JW Vaughan ACM Transactions on Economics and Computation (TEAC) 1 (2), 1-39, 2013 | 116 | 2013 |
| Low-rank matrix factorization with attributes J Abernethy, F Bach, T Evgeniou, JP Vert arXiv preprint cs/0611124, 2006 | 115 | 2006 |
| A stochastic view of optimal regret through minimax duality J Abernethy, A Agarwal, PL Bartlett, A Rakhlin arXiv preprint arXiv:0903.5328, 2009 | 110 | 2009 |
| Web spam identification through content and hyperlinks J Abernethy, O Chapelle, C Castillo Proceedings of the 4th international workshop on Adversarial information …, 2008 | 107 | 2008 |
| Online linear optimization via smoothing J Abernethy, C Lee, A Sinha, A Tewari Conference on learning theory, 807-823, 2014 | 101 | 2014 |
| Fighting bandits with a new kind of smoothness JD Abernethy, C Lee, A Tewari Advances in Neural Information Processing Systems 28, 2015 | 97 | 2015 |
| Graph regularization methods for web spam detection J Abernethy, O Chapelle, C Castillo Machine Learning 81 (2), 207-225, 2010 | 88 | 2010 |
| A collaborative mechanism for crowdsourcing prediction problems JD Abernethy, R Frongillo Advances in neural information processing systems 24, 2011 | 82 | 2011 |
| A characterization of scoring rules for linear properties JD Abernethy, RM Frongillo Conference on Learning Theory, 27.1-27.13, 2012 | 80 | 2012 |
| Eliciting consumer preferences using robust adaptive choice questionnaires J Abernethy, T Evgeniou, O Toubia, JP Vert IEEE Transactions on Knowledge and Data Engineering 20 (2), 145-155, 2007 | 80 | 2007 |
| Interior-point methods for full-information and bandit online learning JD Abernethy, E Hazan, A Rakhlin IEEE Transactions on Information Theory 58 (7), 4164-4175, 2012 | 79 | 2012 |
| Active sampling for min-max fairness J Abernethy, P Awasthi, M Kleindessner, J Morgenstern, C Russell, ... arXiv preprint arXiv:2006.06879, 2020 | 76 | 2020 |
| Beating the adaptive bandit with high probability J Abernethy, A Rakhlin 2009 Information Theory and Applications Workshop, 280-289, 2009 | 75 | 2009 |
| Faster rates for convex-concave games J Abernethy, KA Lai, KY Levy, JK Wang Conference On Learning Theory, 1595-1625, 2018 | 70 | 2018 |
Peter BartlettProfessor, EECS and Statistics, UC BerkeleyVerified email at cs.berkeley.edu
