Michael I. Jordan - arXivDaily 作者

1810.00828 2020-04-30 math.ST stat.ML stat.TH

Singularity, Misspecification, and the Convergence Rate of EM

Raaz Dwivedi, Nhat Ho, Koulik Khamaru, Michael I. Jordan, Martin J. Wainwright, Bin Yu

Comments 63 pages, 12 figures. The first three authors contributed equally to this work. To appear in Annals of Statistics

1904.02144 2020-04-29 cs.LG cs.CR math.OC stat.ML

HopSkipJumpAttack: A Query-Efficient Decision-Based Attack

Jianbo Chen, Michael I. Jordan, Martin J. Wainwright

2004.06977 2020-04-16 cs.LG math.AP math.OC stat.ML

On Learning Rates and Schrödinger Operators

Bin Shi, Weijie J. Su, Michael I. Jordan

Comments 49 pages, 21 figures

2004.04719 2020-04-10 stat.ML cs.LG math.OC math.ST stat.TH

On Linear Stochastic Approximation: Fine-grained Polyak-Ruppert and Non-Asymptotic Concentration

Wenlong Mou, Chris Junchi Li, Martin J. Wainwright, Peter L. Bartlett, Michael I. Jordan

2003.07337 2020-03-17 stat.ML cs.LG math.OC

Is Temporal Difference Learning Optimal? An Instance-Dependent Analysis

Koulik Khamaru, Ashwin Pananjady, Feng Ruan, Martin J. Wainwright, Michael I. Jordan

Comments 38 pages, 3 figures

2003.05955 2020-03-16 cs.LG stat.ML

Post-Estimation Smoothing: A Simple Baseline for Learning with Side Information

Esther Rolf, Michael I. Jordan, Benjamin Recht

Comments To appear in AISTATS 2020

2003.02932 2020-03-09 cs.LG stat.ML

Robustness Guarantees for Mode Estimation with an Application to Bandits

Aldo Pacchiano, Heinrich Jiang, Michael I. Jordan

Comments 12 pages, 7 figures, 14 appendix pages

1906.04349 2020-03-05 cs.LG stat.ML

Learning to Score Behaviors for Guided Policy Optimization

Aldo Pacchiano, Jack Parker-Holder, Yunhao Tang, Anna Choromanska, Krzysztof Choromanski, Michael I. Jordan

1907.01127 2020-03-03 cs.LG math.OC stat.ML

Convergence Rates of Smooth Message Passing with Rounding in Entropy-Regularized MAP Inference

Jonathan N. Lee, Aldo Pacchiano, Michael I. Jordan

1905.13285 2020-02-26 stat.ML cs.LG stat.CO

Langevin Monte Carlo without smoothness

Niladri S. Chatterji, Jelena Diakonikolas, Michael I. Jordan, Peter L. Bartlett

Comments Updated to match the AISTATS 2020 camera ready version. Some example applications added and typos corrected

2002.05359 2020-02-14 cs.LG math.OC stat.ML

Adaptivity of Stochastic Gradient Methods for Nonconvex Optimization

Samuel Horváth, Lihua Lei, Peter Richtárik, Michael I. Jordan

Comments 11 pages, 4 Figures, 20 pages Appendix

1806.00550 2020-02-10 stat.ME

A Swiss Army Infinitesimal Jackknife

Ryan Giordano, Will Stephenson, Runjing Liu, Michael I. Jordan, Tamara Broderick

Comments Accepted at AISTATS 2019

1811.08393 2020-02-04 cs.LG cs.DS cs.NE stat.ML

Gen-Oja: A Two-time-scale approach for Streaming CCA

Kush Bhatia, Aldo Pacchiano, Nicolas Flammarion, Peter L. Bartlett, Michael I. Jordan

Comments Accepted at NeurIPS 2018

2001.09623 2020-01-28 cs.LG stat.ML

Variance Reduction with Sparse Gradients

Melih Elibol, Lihua Lei, Michael I. Jordan

Comments ICLR 2020

1702.02279 2020-01-22 cs.IT cs.DS math.IT

Decoding from Pooled Data: Phase Transitions of Message Passing

Ahmed El Alaoui, Aaditya Ramdas, Florent Krzakala, Lenka Zdeborova, Michael I. Jordan

Journal ref IEEE Transactions on Information Theory (Volume: 65 , Issue: 1 , Jan. 2019)

1907.03712 2019-12-18 cs.LG stat.ML

Policy-Gradient Algorithms Have No Guarantees of Convergence in Linear Quadratic Games

Eric Mazumdar, Lillian J. Ratliff, Michael I. Jordan, S. Shankar Sastry

1912.05153 2019-12-12 stat.ML cs.DS cs.LG math.PR stat.CO

Sampling for Bayesian Mixture Models: MCMC with Polynomial-Time Mixing

Wenlong Mou, Nhat Ho, Martin J. Wainwright, Peter L. Bartlett, Michael I. Jordan

1811.02657 2019-12-10 cs.CV cs.AI cs.LG cs.NE stat.ML

A Bayesian Perspective of Convolutional Neural Networks through a Deconvolutional Generative Model

Tan Nguyen, Nhat Ho, Ankit Patel, Anima Anandkumar, Michael I. Jordan, Richard G. Baraniuk

Comments Keywords: neural nets, generative models, semi-supervised learning, cross-entropy, statistical guarantees 80 pages, 7 figures, 8 tables

1904.03257 2019-12-03 cs.LG cs.DB cs.DC cs.SE stat.ML

MLSys: The New Frontier of Machine Learning Systems

Alexander Ratner, Dan Alistarh, Gustavo Alonso, David G. Andersen, Peter Bailis, Sarah Bird, Nicholas Carlini, Bryan Catanzaro, Jennifer Chayes, Eric Chung, Bill Dally, Jeff Dean, Inderjit S. Dhillon, Alexandros Dimakis, Pradeep Dubey, Charles Elkan, Grigori Fursin, Gregory R. Ganger, Lise Getoor, Phillip B. Gibbons, Garth A. Gibson, Joseph E. Gonzalez, Justin Gottschlich, Song Han, Kim Hazelwood, Furong Huang, Martin Jaggi, Kevin Jamieson, Michael I. Jordan, Gauri Joshi, Rania Khalaf, Jason Knight, Jakub Konečný, Tim Kraska, Arun Kumar, Anastasios Kyrillidis, Aparna Lakshmiratan, Jing Li, Samuel Madden, H. Brendan McMahan, Erik Meijer, Ioannis Mitliagkas, Rajat Monga, Derek Murray, Kunle Olukotun, Dimitris Papailiopoulos, Gennady Pekhimenko, Theodoros Rekatsinas, Afshin Rostamizadeh, Christopher Ré, Christopher De Sa, Hanie Sedghi, Siddhartha Sen, Virginia Smith, Alex Smola, Dawn Song, Evan Sparks, Ion Stoica, Vivienne Sze, Madeleine Udell, Joaquin Vanschoren, Shivaram Venkataraman, Rashmi Vinayak, Markus Weimer, Andrew Gordon Wilson, Eric Xing, Matei Zaharia, Ce Zhang, Ameet Talwalkar

1902.02495 2019-11-12 stat.ML cs.LG

Cost-Effective Incentive Allocation via Structured Counterfactual Inference

Romain Lopez, Chenchen Li, Xiang Yan, Junwu Xiong, Michael I. Jordan, Yuan Qi, Le Song

Journal ref Association for the Advancement of Artificial Intelligence (AAAI) 2020

1902.03694 2019-11-05 math.OC cs.LG cs.NA math.NA stat.ML

Acceleration via Symplectic Discretization of High-Resolution Differential Equations

Bin Shi, Simon S. Du, Weijie J. Su, Michael I. Jordan

Comments Published in Neurips 2019

1902.00996 2019-10-23 stat.ML cs.LG cs.NA math.NA

Is There an Analog of Nesterov Acceleration for MCMC?

Yi-An Ma, Niladri Chatterji, Xiang Cheng, Nicolas Flammarion, Peter Bartlett, Michael I. Jordan

1909.12031 2019-09-27 cs.LG stat.ML

Towards Understanding the Transferability of Deep Representations

Hong Liu, Mingsheng Long, Jianmin Wang, Michael I. Jordan

1908.01878 2019-09-27 cs.LG stat.ML

How Does Learning Rate Decay Help Modern Neural Networks?

Kaichao You, Mingsheng Long, Jianmin Wang, Michael I. Jordan

Comments title changed

1902.04811 2019-09-05 cs.LG math.OC stat.ML

On Nonconvex Optimization for Machine Learning: Gradients, Stochasticity, and Saddle Points

Chi Jin, Praneeth Netrapalli, Rong Ge, Sham M. Kakade, Michael I. Jordan

Comments A preliminary version of this paper, with a subset of the results that are presented here, was presented at ICML 2017 (also as arXiv:1703.00887)

1907.05388 2019-08-09 cs.LG math.OC stat.ML

Provably Efficient Reinforcement Learning with Linear Function Approximation

Chi Jin, Zhuoran Yang, Zhaoran Wang, Michael I. Jordan

1703.06222 2019-08-07 stat.ME math.ST stat.ML stat.TH

A unified treatment of multiple testing with prior knowledge using the p-filter

Aaditya Ramdas, Rina Foygel Barber, Martin J. Wainwright, Michael I. Jordan

Comments 36 pages, 1 figure, accepted for publication at the Annals of Statistics

1907.12116 2019-07-30 math.ST cs.LG stat.ML stat.TH

A Higher-Order Swiss Army Infinitesimal Jackknife

Ryan Giordano, Michael I. Jordan, Tamara Broderick

1907.11826 2019-07-30 stat.ML cs.LG stat.CO

Bayesian Robustness: A Nonasymptotic Viewpoint

Kush Bhatia, Yi-An Ma, Anca D. Dragan, Peter L. Bartlett, Michael I. Jordan

Comments 30 pages, 5 figures

1904.05801 2019-07-24 cs.LG stat.ML

Bridging Theory and Algorithm for Domain Adaptation

Yuchen Zhang, Tianle Liu, Mingsheng Long, Michael I. Jordan

Comments Proceedings of the 36th International Conference on Machine Learning, Long Beach, California, PMLR 97, 2019