Peter Bartlett's 2017-2022 Papers

[HB17] Fares Hedayati and Peter L. Bartlett. Exchangeability characterizes optimality of sequential normalized maximum likelihood and Bayesian prediction. IEEE Transactions on Information Theory, 63(10):6767--6773, October 2017. [ bib | DOI | .pdf | .pdf | Abstract ]
[AYMBG17] Yasin Abbasi-Yadkori, Alan Malek, Peter L. Bartlett, and Victor Gabillon. Hit-and-run for sampling and planning in non-convex spaces. In Aarti Singh and Jerry Zhu, editors, Proceedings of the 20th International Conference on Artificial Intelligence and Statistics, volume 54 of Proceedings of Machine Learning Research, pages 888--895, Fort Lauderdale, FL, USA, 2017. [ bib | .pdf | Abstract ]
[ZSJ+17] Kai Zhong, Zhao Song, Prateek Jain, Peter L. Bartlett, and Inderjit S. Dhillon. Recovery guarantees for one-hidden-layer neural networks. In Doina Precup and Yee Whye Teh, editors, Proceedings of the 34th International Conference on Machine Learning (ICML-17), volume 70 of Proceedings of Machine Learning Research, pages 4140--4149. PMLR, 2017. [ bib | .html | .pdf | Abstract ]
[PBBC17] Martin Péron, Kai Helge Becker, Peter L. Bartlett, and Iadine Chadès. Fast-tracking stationary MOMDPs for adaptive management problems. In Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence (AAAI-17), pages 4531--4537, 2017. [ bib | http | http | Abstract ]
[AYBG17] Yasin Abbasi-Yadkori, Peter L. Bartlett, and Victor Gabillon. Near minimax optimal players for the finite-time 3-expert prediction problem. In I. Guyon, U. V. Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett, editors, Advances in Neural Information Processing Systems 30, pages 3033--3042. Curran Associates, Inc., 2017. [ bib | .pdf | .pdf | Abstract ]
[BFT17] Peter Bartlett, Dylan Foster, and Matus Telgarsky. Spectrally-normalized margin bounds for neural networks. In I. Guyon, U. V. Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett, editors, Advances in Neural Information Processing Systems 30, pages 6240--6249. Curran Associates, Inc., 2017. [ bib | .pdf | .pdf | Abstract ]
[BHLM17] Peter L. Bartlett, Nick Harvey, Chris Liaw, and Abbas Mehrabian. Nearly-tight VC-dimension and pseudodimension bounds for piecewise linear neural networks. Technical Report 1703.02930, arXiv.org, 2017. [ bib | http | .pdf | Abstract ]
[KB17] Walid Krichene and Peter Bartlett. Acceleration and averaging in stochastic descent dynamics. In I. Guyon, U. V. Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett, editors, Advances in Neural Information Processing Systems 30, pages 6796--6806. Curran Associates, Inc., 2017. [ bib | .pdf | .pdf | Abstract ]
[CB17] Niladri Chatterji and Peter Bartlett. Alternating minimization for dictionary learning with random initialization. In I. Guyon, U. V. Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett, editors, Advances in Neural Information Processing Systems 30, pages 1997--2006. Curran Associates, Inc., 2017. [ bib | .pdf | .pdf ]
[BEL18] Peter L. Bartlett, Steven Evans, and Philip M. Long. Representing smooth functions as compositions of near-identity functions with implications for deep network optimization. Technical Report 1804.05012, arXiv.org, 2018. [ bib | http | .pdf | Abstract ]
[YPL+18] Dong Yin, Ashwin Pananjady, Max Lam, Dimitris Papailiopoulos, Kannan Ramchandran, and Peter Bartlett. Gradient diversity: a key ingredient for scalable distributed learning. In Amos Storkey and Fernando Perez-Cruz, editors, Proceedings of the 21st International Conference on Artificial Intelligence and Statistics, volume 84 of Proceedings of Machine Learning Research, pages 1998--2007. PMLR, 2018. [ bib | .html | .pdf | Abstract ]
[CRP+18] Xiang Cheng, Fred Roosta, Stefan Palombo, Peter Bartlett, and Michael Mahoney. Flag nā€™ flare: Fast linearly-coupled adaptive gradient methods. In Amos Storkey and Fernando Perez-Cruz, editors, Proceedings of the 21st International Conference on Artificial Intelligence and Statistics, volume 84 of Proceedings of Machine Learning Research, pages 404--414. PMLR, 2018. [ bib | .html | .pdf | Abstract ]
[CB18] Xiang Cheng and Peter Bartlett. Convergence of Langevin MCMC in KL-divergence. In Firdaus Janoos, Mehryar Mohri, and Karthik Sridharan, editors, Proceedings of ALT2018, volume 83 of Proceedings of Machine Learning Research, pages 186--211. PMLR, 2018. [ bib | .html | .pdf | Abstract ]
[PBB+18] Martin Péron, Peter Bartlett, Kai Helge Becker, Kate Helmstedt, and Iadine Chadès. Two approximate dynamic programming algorithms for managing complete SIS networks. In ACM SIGCAS Conference on Computing and Sustainable Societies (COMPASS 2018), 2018. [ bib | http | .pdf ]
[YCRB18] Dong Yin, Yudong Chen, Kannan Ramchandran, and Peter Bartlett. Byzantine-robust distributed learning: Towards optimal statistical rates. In Jennifer Dy and Andreas Krause, editors, Proceedings of the 35th International Conference on Machine Learning (ICML-18), volume 80 of Proceedings of Machine Learning Research, pages 5650--5659. PMLR, 2018. [ bib | .html | .pdf | Abstract ]
[CFM+18] Niladri Chatterji, Nicolas Flammarion, Yian Ma, Peter Bartlett, and Michael Jordan. On the theory of variance reduction for stochastic gradient Monte Carlo. In Jennifer Dy and Andreas Krause, editors, Proceedings of the 35th International Conference on Machine Learning (ICML-18), volume 80 of Proceedings of Machine Learning Research, pages 764--773. PMLR, 2018. [ bib | .html | .pdf | Abstract ]
[BHL18] Peter L. Bartlett, David P. Helmbold, and Philip M. Long. Gradient descent with identity initialization efficiently learns positive definite linear transformations by deep residual networks. In Jennifer Dy and Andreas Krause, editors, Proceedings of the 35th International Conference on Machine Learning (ICML-18), volume 80 of Proceedings of Machine Learning Research, pages 521--530. PMLR, 2018. [ bib | http | .pdf | Abstract ]
[MB18] Alan Malek and Peter L. Bartlett. Horizon-independent minimax linear regression. In S. Bengio, H. Wallach, H. Larochelle, K. Grauman, N. Cesa-Bianchi, and R. Garnett, editors, Advances in Neural Information Processing Systems 31, pages 5264--5273. Curran Associates, Inc., 2018. [ bib | .pdf | Abstract ]
[CCBJ18] Xiang Cheng, Niladri S. Chatterji, Peter L. Bartlett, and Michael I. Jordan. Underdamped Langevin MCMC: A non-asymptotic analysis. In Sébastien Bubeck, Vianney Perchet, and Philippe Rigollet, editors, Proceedings of the 31st Conference on Learning Theory (COLT2018), volume 75 of Proceedings of Machine Learning Research, pages 300--323. PMLR, 2018. [ bib | .html | .pdf | Abstract ]
[AYBG+18] Yasin Abbasi-Yadkori, Peter L. Bartlett, Victor Gabillon, Alan Malek, and Michal Valko. Best of both worlds: Stochastic and adversarial best-arm identification. In Sébastien Bubeck, Vianney Perchet, and Philippe Rigollet, editors, Proceedings of the 31st Conference on Learning Theory (COLT2018), volume 75 of Proceedings of Machine Learning Research, pages 918--949. PMLR, 2018. [ bib | http | .pdf | Abstract ]
[BPF+18] Kush Bhatia, Aldo Pacchiano, Nicolas Flammarion, Peter L. Bartlett, and Michael I. Jordan. Gen-Oja: Simple and efficient algorithm for streaming generalized eigenvector computation. In S. Bengio, H. Wallach, H. Larochelle, K. Grauman, N. Cesa-Bianchi, and R. Garnett, editors, Advances in Neural Information Processing Systems 31, pages 7016--7025. Curran Associates, Inc., 2018. [ bib | .pdf | Abstract ]
[CCAY+18] Xiang Cheng, Niladri S. Chatterji, Yasin Abbasi-Yadkori, Peter L. Bartlett, and Michael I. Jordan. Sharp convergence rates for Langevin dynamics in the nonconvex setting. Technical Report arXiv:1805.01648 [stat.ML], arxiv.org, 2018. [ bib | http ]
[BHLM19] Peter L. Bartlett, Nick Harvey, Christopher Liaw, and Abbas Mehrabian. Nearly-tight VC-dimension and pseudodimension bounds for piecewise linear neural networks. Journal of Machine Learning Research, 20(63):1--17, 2019. [ bib | .html ]
[BGV19] Peter L. Bartlett, Victor Gabillon, and Michal Valko. A simple parameter-free and adaptive approach to optimization under a minimal local smoothness assumption. In Aurélien Garivier and Satyen Kale, editors, Proceedings of the 30th International Conference on Algorithmic Learning Theory, volume 98 of Proceedings of Machine Learning Research, pages 184--206, Chicago, Illinois, 2019. PMLR. [ bib | .html | .pdf | Abstract ]
[MPB+19] Dhruv Malik, Ashwin Pananjady, Kush Bhatia, Koulik Khamaru, Peter L. Bartlett, and Martin J. Wainwright. Derivative-free methods for policy optimization: Guarantees for linear quadratic systems. In Kamalika Chaudhuri and Masashi Sugiyama, editors, Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics (AISTATS), volume 89 of Proceedings of Machine Learning Research, pages 2916--2925. PMLR, 2019. [ bib | .html | .pdf | Abstract ]
[MRSB19] Vidya Muthukumar, Mitas Ray, Anant Sahai, and Peter L. Bartlett. Best of many worlds: Robust model selection for online supervised learning. In Kamalika Chaudhuri and Masashi Sugiyama, editors, Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics (AISTATS), volume 89 of Proceedings of Machine Learning Research, pages 3177--3186. PMLR, 2019. [ bib | .html | .pdf | Abstract ]
[CPB19] Niladri Chatterji, Aldo Pacchiano, and Peter Bartlett. Online learning with kernel losses. In Kamalika Chaudhuri and Ruslan Salakhutdinov, editors, Proceedings of the 36th International Conference on Machine Learning, volume 97 of Proceedings of Machine Learning Research, pages 971--980, Long Beach, California, USA, 2019. PMLR. [ bib | .html | .pdf | Abstract ]
[BGHV19] Peter L. Bartlett, Victor Gabillon, Jennifer Healey, and Michal Valko. Scale-free adaptive planning for deterministic dynamics and discounted rewards. In Kamalika Chaudhuri and Ruslan Salakhutdinov, editors, Proceedings of the 36th International Conference on Machine Learning, volume 97 of Proceedings of Machine Learning Research, pages 495--504, Long Beach, California, USA, 2019. PMLR. [ bib | .html | .pdf | Abstract ]
[AYBB+19] Yasin Abbasi-Yadkori, Peter L. Bartlett, Kush Bhatia, Nevena Lazic, Csaba Szepesvari, and Gellert Weisz. POLITEX: Regret bounds for policy iteration using expert prediction. In Kamalika Chaudhuri and Ruslan Salakhutdinov, editors, Proceedings of the 36th International Conference on Machine Learning, volume 97 of Proceedings of Machine Learning Research, pages 3692--3702, Long Beach, California, USA, 2019. PMLR. [ bib | .html | .pdf | Abstract ]
[YCKB19] Dong Yin, Yudong Chen, Ramchandran Kannan, and Peter L. Bartlett. Defending against saddle point attack in Byzantine-robust distributed learning. In Kamalika Chaudhuri and Ruslan Salakhutdinov, editors, Proceedings of the 36th International Conference on Machine Learning, volume 97 of Proceedings of Machine Learning Research, pages 7074--7084, Long Beach, California, USA, 2019. PMLR. [ bib | .html | .pdf | Abstract ]
[YKB19] Dong Yin, Ramchandran Kannan, and Peter L. Bartlett. Rademacher complexity for adversarially robust generalization. In Kamalika Chaudhuri and Ruslan Salakhutdinov, editors, Proceedings of the 36th International Conference on Machine Learning, volume 97 of Proceedings of Machine Learning Research, pages 7085--7094, Long Beach, California, USA, 2019. PMLR. [ bib | .html | .pdf | Abstract ]
[BMD+19] Kush Bhatia, Yi-An Ma, Anca D. Dragan, Peter L. Bartlett, and Michael I. Jordan. Bayesian robustness: A nonasymptotic viewpoint. Technical Report 1907.11826, arXiv, 2019. [ bib ]
[MHW+19] Wenlong Mou, Nhat Ho, Martin J. Wainwright, Peter L. Bartlett, and Michael I. Jordan. Sampling for Bayesian mixture models: MCMC with polynomial-time mixing. Technical Report 1912.05153, arXiv, 2019. [ bib | Abstract ]
[CFB19] Yeshwanth Cherapanamjeri, Nicolas Flammarion, and Peter L. Bartlett. Fast mean estimation with sub-gaussian rates. In Alina Beygelzimer and Daniel Hsu, editors, Proceedings of the Thirty-Second Conference on Learning Theory, volume 99 of Proceedings of Machine Learning Research, pages 786--806. PMLR, 2019. [ bib | .html | .pdf | Abstract ]
[CB19] Yeshwanth Cherapanamjeri and Peter L. Bartlett. Testing Markov chains without hitting. In Alina Beygelzimer and Daniel Hsu, editors, Proceedings of the 32nd Conference on Learning Theory (COLT2019), volume 99 of Proceedings of Machine Learning Research, pages 758--785. PMLR, 2019. [ bib | .html | .pdf | Abstract ]
[BHL19] Peter L. Bartlett, David P. Helmbold, and Philip M. Long. Gradient descent with identity initialization efficiently learns positive definite linear transformations by deep residual networks. Neural Computation, 31:477--502, 2019. [ bib ]
[MFWB19] Wenlong Mou, Nicolas Flammarion, Martin J. Wainwright, and Peter L. Bartlett. An efficient sampling algorithm for non-smooth composite potentials. Technical Report 1910.00551, arXiv, 2019. [ bib ]
[TB20] Alexander Tsigler and Peter L. Bartlett. Benign overfitting in ridge regression. Technical Report arXiv:2009.14286, arxiv.org, 2020. [ bib | http | Abstract ]
[BPB+20] Kush Bhatia, Ashwin Pananjady, Peter L. Bartlett, Anca Dragan, and Martin Wainwright. Preference learning along multiple criteria: A game-theoretic perspective. In H. Larochelle, M. Ranzato, R. Hadsell, M. F. Balcan, and H. Lin, editors, Advances in Neural Information Processing Systems, volume 33, pages 7413--7424. Curran Associates, Inc., 2020. [ bib | .pdf | Abstract ]
[MPB+20] Dhruv Malik, Ashwin Pananjady, Kush Bhatia, Koulik Khamaru, Peter L. Bartlett, and Martin J. Wainwright. Derivative-free methods for policy optimization: Guarantees for linear quadratic systems. Journal of Machine Learning Research, 21(21):1--51, 2020. [ bib | .html ]
[CMB20] Niladri Chatterji, Vidya Muthukumar, and Peter L. Bartlett. OSOM: A simultaneously optimal algorithm for multi-armed and linear contextual bandits. In Silvia Chiappa and Roberto Calandra, editors, Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics, volume 108 of Proceedings of Machine Learning Research, pages 1844--1854. PMLR, 26--28 Aug 2020. [ bib | .html | .pdf | Abstract ]
[CDJB20] Niladri Chatterji, Jelena Diakonikolas, Michael I. Jordan, and Peter L. Bartlett. Langevin Monte Carlo without smoothness. In Silvia Chiappa and Roberto Calandra, editors, Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics, volume 108 of Proceedings of Machine Learning Research, pages 1716--1726. PMLR, 26--28 Aug 2020. [ bib | .html | .pdf | Abstract ]
[BLLT20] Peter L. Bartlett, Philip M. Long, Gábor Lugosi, and Alexander Tsigler. Benign overfitting in linear regression. Proceedings of the National Academy of Sciences, 117(48):30063--30070, 2020. (arXiv:1906.11300). [ bib | DOI | arXiv | http | Abstract ]
[MPM+20] Eric Mazumdar, Aldo Pacchiano, Yian Ma, Michael Jordan, and Peter Bartlett. On approximate Thompson sampling with Langevin algorithms. In Hal Daumé III and Aarti Singh, editors, Proceedings of the 37th International Conference on Machine Learning, volume 119 of Proceedings of Machine Learning Research, pages 6797--6807. PMLR, 13--18 Jul 2020. [ bib | .html | .pdf | Abstract ]
[LPBJ20] Jonathan Lee, Aldo Pacchiano, Peter L. Bartlett, and Michael I. Jordan. Accelerated message passing for entropy-regularized MAP inference. In Hal Daumé III and Aarti Singh, editors, Proceedings of the 37th International Conference on Machine Learning, volume 119 of Proceedings of Machine Learning Research, pages 5736--5746. PMLR, 13--18 Jul 2020. [ bib | .html | .pdf | Abstract ]
[CYBJ20] Xiang Cheng, Dong Yin, Peter Bartlett, and Michael Jordan. Stochastic gradient and Langevin processes. In Hal Daumé III and Aarti Singh, editors, Proceedings of the 37th International Conference on Machine Learning, volume 119 of Proceedings of Machine Learning Research, pages 1810--1819. PMLR, 13--18 Jul 2020. [ bib | .html | .pdf | Abstract ]
[MFB20] Hossein Mobahi, Mehrdad Farajtabar, and Peter L. Bartlett. Self-distillation amplifies regularization in Hilbert space. In H. Larochelle, M. Ranzato, R. Hadsell, M. F. Balcan, and H. Lin, editors, Advances in Neural Information Processing Systems 33, volume 33, pages 3351--3361. Curran Associates, Inc., 2020. [ bib | .pdf | Abstract ]
[CAT+20] Yeshwanth Cherapanamjeri, Efe Aras, Nilesh Tripuraneni, Michael I. Jordan, Nicolas Flammarion, and Peter L. Bartlett. Optimal robust linear regression in nearly linear time. Technical Report 2007.08137, arXiv, 2020. [ bib ]
[MLW+20] Wenlong Mou, Chris Junchi Li, Martin J Wainwright, Peter L Bartlett, and Michael I Jordan. On linear stochastic approximation: Fine-grained Polyak-Ruppert and non-asymptotic concentration. In Jacob Abernethy and Shivani Agarwal, editors, Proceedings of Thirty Third Conference on Learning Theory, volume 125 of Proceedings of Machine Learning Research, pages 2947--2997. PMLR, 2020. [ bib | .html | .pdf | Abstract ]
[BL20] Peter L. Bartlett and Philip M. Long. Failures of model-dependent generalization bounds for least-norm interpolation. Technical Report arXiv:2010.08479, arxiv.org, 2020. [ bib | http | Abstract ]
[CTBJ20] Yeshwanth Cherapanamjeri, Nilesh Tripuraneni, Peter L. Bartlett, and Michael I. Jordan. Optimal mean estimation without a variance. Technical Report 2011.12433, arXiv, 2020. [ bib ]
[BMR21] Peter L. Bartlett, Andrea Montanari, and Alexander Rakhlin. Deep learning: a statistical viewpoint. Acta Numerica, 30:87ā€“201, 2021. [ bib | DOI | http | Abstract ]
[BL21] Peter L. Bartlett and Philip M. Long. Failures of model-dependent generalization bounds for least-norm interpolation. Journal of Machine Learning Research, 22(204):1--15, 2021. arXiv:2010.08479. [ bib | .html ]
[MMW+21] Wenlong Mou, Yi-An Ma, Martin J. Wainwright, Peter L. Bartlett, and Michael I. Jordan. High-order Langevin diffusion yields an accelerated MCMC algorithm. Journal of Machine Learning Research, 22(42):1--41, 2021. [ bib | .html ]
[MCC+21] Yi-An Ma, Niladri S. Chatterji, Xiang Cheng, Nicolas Flammarion, Peter L. Bartlett, and Michael I. Jordan. Is there an analog of Nesterov acceleration for gradient-based MCMC? Bernoulli, 27(3):1942--1992, 2021. [ bib | DOI | Abstract ]
[BBDS21] Kush Bhatia, Peter L. Bartlett, Anca D. Dragan, and Jacob Steinhardt. Agnostic Learning with Unknown Utilities. In James R. Lee, editor, 12th Innovations in Theoretical Computer Science Conference (ITCS 2021), volume 185 of Leibniz International Proceedings in Informatics (LIPIcs), pages 55:1--55:20, Dagstuhl, Germany, 2021. Schloss Dagstuhl--Leibniz-Zentrum für Informatik. [ bib | DOI | http ]
[PGBJ21] Aldo Pacchiano, Mohammad Ghavamzadeh, Peter L. Bartlett, and Heinrich Jiang. Stochastic bandits with linear constraints. In Arindam Banerjee and Kenji Fukumizu, editors, Proceedings of The 24th International Conference on Artificial Intelligence and Statistics, volume 130 of Proceedings of Machine Learning Research, pages 2827--2835. PMLR, 13--15 Apr 2021. [ bib | .html | .pdf | Abstract ]
[ABMS21] Raman Arora, Peter L. Bartlett, Poorya Mianjy, and Nathan Srebro. Dropout: Explicit forms and capacity control. In Marina Meila and Tong Zhang, editors, Proceedings of the 38th International Conference on Machine Learning, volume 139 of Proceedings of Machine Learning Research, pages 351--361. PMLR, 18--24 Jul 2021. [ bib | .html | .pdf | Abstract ]
[CLB21b] Niladri S. Chatterji, Philip M. Long, and Peter L. Bartlett. When does gradient descent with logistic loss interpolate using deep networks with smoothed ReLU activations? In Mikhail Belkin and Samory Kpotufe, editors, Proceedings of the 34th Conference on Learning Theory (COLT2021), volume 134 of Proceedings of Machine Learning Research, pages 927--1027, 2021. [ bib | .html | Abstract ]
[PSAB21] Juan Perdomo, Max Simchowitz, Alekh Agarwal, and Peter L. Bartlett. Towards a dimension-free understanding of adaptive linear control. In Proceedings of the 34th Conference on Learning Theory (COLT2021), 2021. To appear. [ bib | Abstract ]
[BBC21] Peter L. Bartlett, Sebastien Bubeck, and Yeshwanth Cherapanamjeri. Adversarial examples in multi-layer random ReLU networks. Technical Report 2106.12611, arXiv, 2021. [ bib | Abstract ]
[CLB21a] Niladri S. Chatterji, Philip M. Long, and Peter L. Bartlett. When does gradient descent with logistic loss find interpolating two-layer networks? Journal of Machine Learning Research, 22(159):1--48, 2021. [ bib | http | Abstract ]
[CBL22] Niladri S. Chatterji, Peter L. Bartlett, and Philip M. Long. Oracle lower bounds for stochastic gradient sampling algorithms. Bernoulli, 28(2):1074--1092, 2022. arXiv:2002.00291. [ bib | http | Abstract ]
[MFWB22] Wenlong Mou, Nicolas Flammarion, Martin J. Wainwright, and Peter L. Bartlett. Improved bounds for discretization of Langevin diffusions: Near-optimal rates without convexity. Bernoulli, 28(3):1577--1601, 2022. [ bib | DOI | http | Abstract ]
[MPWB22] Wenlong Mou, Ashwin Pananjady, Martin J. Wainwright, and Peter L. Bartlett. Optimal and instance-dependent guarantees for Markovian linear stochastic approximation. In Proceedings of the 35th Conference on Learning Theory (COLT2022), 2022. To appear. [ bib | Abstract ]
[FCB22] Spencer Frei, Niladri Chatterji, and Peter L. Bartlett. Benign overfitting without linearity: Neural network classifiers trained by gradient descent for noisy linear data. In Proceedings of the 35th Conference on Learning Theory (COLT2022), 2022. To appear. [ bib | Abstract ]
[BIW22] Peter L. Bartlett, Piotr Indyk, and Tal Wagner. Generalization bounds for data-driven numerical linear algebra. In Proceedings of the 35th Conference on Learning Theory (COLT2022), 2022. To appear. [ bib | Abstract ]
[CTBJ22] Yeshwanth Cherapanamjeri, Nilesh Tripuraneni, Peter L. Bartlett, and Michael I. Jordan. Optimal mean estimation without a variance. In Proceedings of the 35th Conference on Learning Theory (COLT2022), 2022. To appear. [ bib | Abstract ]
[CLB22] Niladri S. Chatterji, Philip M. Long, and Peter L. Bartlett. The interplay between implicit bias and benign overfitting in two-layer linear networks. Journal of Machine Learning Research, 2022. to appear. [ bib ]

This file was generated by bibtex2html 1.98.

Books

Journal papers, book chapters

All Publications