Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Ashwin Pananjady

Ashwin Pananjady

Preference learning along multiple criteria: A game-theoretic perspective


May 05, 2021
Kush Bhatia, Ashwin Pananjady, Peter L. Bartlett, Anca D. Dragan, Martin J. Wainwright

Figure 1 for Preference learning along multiple criteria: A game-theoretic perspective
Figure 2 for Preference learning along multiple criteria: A game-theoretic perspective
Figure 3 for Preference learning along multiple criteria: A game-theoretic perspective
Figure 4 for Preference learning along multiple criteria: A game-theoretic perspective
* 47 pages; published as a conference paper at NeurIPS 2020 
  Access Paper or Ask Questions

Optimal oracle inequalities for solving projected fixed-point equations


Dec 09, 2020
Wenlong Mou, Ashwin Pananjady, Martin J. Wainwright

Figure 1 for Optimal oracle inequalities for solving projected fixed-point equations
Figure 2 for Optimal oracle inequalities for solving projected fixed-point equations
Figure 3 for Optimal oracle inequalities for solving projected fixed-point equations

  Access Paper or Ask Questions

Isotonic regression with unknown permutations: Statistics, computation, and adaptation


Sep 05, 2020
Ashwin Pananjady, Richard J. Samworth


  Access Paper or Ask Questions

Is Temporal Difference Learning Optimal? An Instance-Dependent Analysis


Mar 16, 2020
Koulik Khamaru, Ashwin Pananjady, Feng Ruan, Martin J. Wainwright, Michael I. Jordan

Figure 1 for Is Temporal Difference Learning Optimal? An Instance-Dependent Analysis
Figure 2 for Is Temporal Difference Learning Optimal? An Instance-Dependent Analysis
Figure 3 for Is Temporal Difference Learning Optimal? An Instance-Dependent Analysis
* 38 pages, 3 figures 
  Access Paper or Ask Questions

Value function estimation in Markov reward processes: Instance-dependent $\ell_\infty$-bounds for policy evaluation


Sep 19, 2019
Ashwin Pananjady, Martin J. Wainwright

Figure 1 for Value function estimation in Markov reward processes: Instance-dependent $\ell_\infty$-bounds for policy evaluation
* 32 pages, 1 figure 
  Access Paper or Ask Questions

Max-Affine Regression: Provable, Tractable, and Near-Optimal Statistical Estimation


Jun 21, 2019
Avishek Ghosh, Ashwin Pananjady, Adityanand Guntuboyina, Kannan Ramchandran

Figure 1 for Max-Affine Regression: Provable, Tractable, and Near-Optimal Statistical Estimation
Figure 2 for Max-Affine Regression: Provable, Tractable, and Near-Optimal Statistical Estimation
Figure 3 for Max-Affine Regression: Provable, Tractable, and Near-Optimal Statistical Estimation
Figure 4 for Max-Affine Regression: Provable, Tractable, and Near-Optimal Statistical Estimation
* The first two authors contributed equally to this work and are ordered alphabetically 
  Access Paper or Ask Questions

Derivative-Free Methods for Policy Optimization: Guarantees for Linear Quadratic Systems


Dec 20, 2018
Dhruv Malik, Ashwin Pananjady, Kush Bhatia, Koulik Khamaru, Peter L. Bartlett, Martin J. Wainwright

Figure 1 for Derivative-Free Methods for Policy Optimization: Guarantees for Linear Quadratic Systems
* 43 pages 
  Access Paper or Ask Questions

Towards Optimal Estimation of Bivariate Isotonic Matrices with Unknown Permutations


Jun 25, 2018
Cheng Mao, Ashwin Pananjady, Martin J. Wainwright

Figure 1 for Towards Optimal Estimation of Bivariate Isotonic Matrices with Unknown Permutations
Figure 2 for Towards Optimal Estimation of Bivariate Isotonic Matrices with Unknown Permutations
* 46 pages, 1 figure. This paper is a longer version of the paper arXiv:1802.09963, v3 of which appeared in part as a 4-page extended abstract at Conference on Learning Theory (COLT) 2018. This paper studies the problem in another metric, and makes the appropriate corrections to Theorem 2 in v1 and v2 of arXiv:1802.09963, which was incorrect as stated and removed in v3 
  Access Paper or Ask Questions

Breaking the $1/\sqrt{n}$ Barrier: Faster Rates for Permutation-based Models in Polynomial Time


Jun 05, 2018
Cheng Mao, Ashwin Pananjady, Martin J. Wainwright

Figure 1 for Breaking the $1/\sqrt{n}$ Barrier: Faster Rates for Permutation-based Models in Polynomial Time
* 30 pages, 1 figure. Accepted for presentation at Conference on Learning Theory (COLT) 2018 
  Access Paper or Ask Questions

Gradient Diversity: a Key Ingredient for Scalable Distributed Learning


Jan 07, 2018
Dong Yin, Ashwin Pananjady, Max Lam, Dimitris Papailiopoulos, Kannan Ramchandran, Peter Bartlett

Figure 1 for Gradient Diversity: a Key Ingredient for Scalable Distributed Learning
Figure 2 for Gradient Diversity: a Key Ingredient for Scalable Distributed Learning
Figure 3 for Gradient Diversity: a Key Ingredient for Scalable Distributed Learning
Figure 4 for Gradient Diversity: a Key Ingredient for Scalable Distributed Learning

  Access Paper or Ask Questions

Worst-case vs Average-case Design for Estimation from Fixed Pairwise Comparisons


Jul 19, 2017
Ashwin Pananjady, Cheng Mao, Vidya Muthukumar, Martin J. Wainwright, Thomas A. Courtade

Figure 1 for Worst-case vs Average-case Design for Estimation from Fixed Pairwise Comparisons
Figure 2 for Worst-case vs Average-case Design for Estimation from Fixed Pairwise Comparisons

  Access Paper or Ask Questions

Denoising Linear Models with Permuted Data


Apr 24, 2017
Ashwin Pananjady, Martin J. Wainwright, Thomas A. Courtade

Figure 1 for Denoising Linear Models with Permuted Data
Figure 2 for Denoising Linear Models with Permuted Data
* To appear in part at ISIT 2017, Aachen 
  Access Paper or Ask Questions

Linear Regression with an Unknown Permutation: Statistical and Computational Limits


Aug 09, 2016
Ashwin Pananjady, Martin J. Wainwright, Thomas A. Courtade

Figure 1 for Linear Regression with an Unknown Permutation: Statistical and Computational Limits
Figure 2 for Linear Regression with an Unknown Permutation: Statistical and Computational Limits
* To appear in part at the 2016 Allerton Conference on Control, Communication and Computing 
  Access Paper or Ask Questions