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 Purushottam Kar

Globally-convergent Iteratively Reweighted Least Squares for Robust Regression Problems


Jun 25, 2020
Bhaskar Mukhoty, Govind Gopakumar, Prateek Jain, Purushottam Kar

* Proceedings of Machine Learning Research (PMLR) 89:313-322, 2019 
* 30 pages, 5 figures, appeared as a publication in the 22nd International Conference on Artificial Intelligence and Statistics (AISTATS), 2019 

  Access Paper or Ask Questions

Epidemiologically and Socio-economically Optimal Policies via Bayesian Optimization


Jun 15, 2020
Amit Chandak, Debojyoti Dey, Bhaskar Mukhoty, Purushottam Kar

* Keywords: COVID-19, Optimal Policy, Lock-down, Epidemiology, Bayesian Optimization Code available at https://github.com/purushottamkar/esop 

  Access Paper or Ask Questions

MACER: A Modular Framework for Accelerated Compilation Error Repair


May 28, 2020
Darshak Chhatbar, Umair Z. Ahmed, Purushottam Kar

* 19 pages, 9 figures. A short version of this paper will appear at the 21st International Conference on Artificial Intelligence in Education (AIED). Code for the MACER tool-chain is available at https://github.com/purushottamkar/macer/ 

  Access Paper or Ask Questions

Accelerating Extreme Classification via Adaptive Feature Agglomeration


May 28, 2019
Ankit Jalan, Purushottam Kar

* A version of this paper without the appendices will appear at the 28th International Joint Conference on Artificial Intelligence (IJCAI 2019). Code for this paper is available at https://github.com/purushottamkar/defrag/ 

  Access Paper or Ask Questions

DANTE: Deep AlterNations for Training nEural networks


Feb 01, 2019
Sneha Kudugunta, Vaibhav B Sinha, Adepu Ravi Sankar, Surya Teja Chavali, Purushottam Kar, Vineeth N Balasubramanian

* 13 pages 

  Access Paper or Ask Questions

Bayes-optimal Hierarchical Classification over Asymmetric Tree-Distance Loss


Feb 17, 2018
Dheeraj Mekala, Vivek Gupta, Purushottam Kar, Harish Karnick

* CS 396 Undergraduate Project Report, 17 Pages 3 Figures 

  Access Paper or Ask Questions

Optimizing Non-decomposable Measures with Deep Networks


Jan 31, 2018
Amartya Sanyal, Pawan Kumar, Purushottam Kar, Sanjay Chawla, Fabrizio Sebastiani


  Access Paper or Ask Questions

Non-convex Optimization for Machine Learning


Dec 21, 2017
Prateek Jain, Purushottam Kar

* Foundations and Trends in Machine Learning: Vol. 10: No. 3-4, pp 142-336 (2017) 
* The official publication is available from now publishers via http://dx.doi.org/10.1561/2200000058 

  Access Paper or Ask Questions

On Context-Dependent Clustering of Bandits


Feb 27, 2017
Claudio Gentile, Shuai Li, Purushottam Kar, Alexandros Karatzoglou, Evans Etrue, Giovanni Zappella


  Access Paper or Ask Questions

Context-Aware Bandits


Feb 26, 2017
Shuai Li, Purushottam Kar

* The paper has been withdrawn as the work has been superseded 

  Access Paper or Ask Questions

Efficient and Consistent Robust Time Series Analysis


Jul 01, 2016
Kush Bhatia, Prateek Jain, Parameswaran Kamalaruban, Purushottam Kar


  Access Paper or Ask Questions

Online Optimization Methods for the Quantification Problem


Jun 13, 2016
Purushottam Kar, Shuai Li, Harikrishna Narasimhan, Sanjay Chawla, Fabrizio Sebastiani

* 26 pages, 6 figures. A short version of this manuscript will appear in the proceedings of the 22nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2016 

  Access Paper or Ask Questions

Locally Non-linear Embeddings for Extreme Multi-label Learning


Jul 09, 2015
Kush Bhatia, Himanshu Jain, Purushottam Kar, Prateek Jain, Manik Varma


  Access Paper or Ask Questions

Robust Regression via Hard Thresholding


Jun 08, 2015
Kush Bhatia, Prateek Jain, Purushottam Kar

* 24 pages, 3 figures 

  Access Paper or Ask Questions

Surrogate Functions for Maximizing Precision at the Top


May 26, 2015
Purushottam Kar, Harikrishna Narasimhan, Prateek Jain

* Journal of Machine Learning Research, W&CP 37 (2015) 
* To appear in the the proceedings of the 32nd International Conference on Machine Learning (ICML 2015) 

  Access Paper or Ask Questions

Optimizing Non-decomposable Performance Measures: A Tale of Two Classes


May 26, 2015
Harikrishna Narasimhan, Purushottam Kar, Prateek Jain

* Journal of Machine Learning Research, W&CP 37 (2015) 
* To appear in proceedings of the 32nd International Conference on Machine Learning (ICML 2015) 

  Access Paper or Ask Questions

Online and Stochastic Gradient Methods for Non-decomposable Loss Functions


Oct 24, 2014
Purushottam Kar, Harikrishna Narasimhan, Prateek Jain

* 25 pages, 3 figures, To appear in the proceedings of the 28th Annual Conference on Neural Information Processing Systems, NIPS 2014 

  Access Paper or Ask Questions

On Iterative Hard Thresholding Methods for High-dimensional M-Estimation


Oct 21, 2014
Prateek Jain, Ambuj Tewari, Purushottam Kar

* 20 pages, 3 figures, To appear in the proceedings of the 28th Annual Conference on Neural Information Processing Systems, NIPS 2014 

  Access Paper or Ask Questions

Large-scale Multi-label Learning with Missing Labels


Nov 25, 2013
Hsiang-Fu Yu, Prateek Jain, Purushottam Kar, Inderjit S. Dhillon


  Access Paper or Ask Questions

On the Generalization Ability of Online Learning Algorithms for Pairwise Loss Functions


May 11, 2013
Purushottam Kar, Bharath K Sriperumbudur, Prateek Jain, Harish C Karnick

* Journal of Machine Learning Research, W&CP 28(3) (2013) 
* To appear in proceedings of the 30th International Conference on Machine Learning (ICML 2013) 

  Access Paper or Ask Questions

On Translation Invariant Kernels and Screw Functions


Feb 18, 2013
Purushottam Kar, Harish Karnick


  Access Paper or Ask Questions

Generalization Guarantees for a Binary Classification Framework for Two-Stage Multiple Kernel Learning


Feb 02, 2013
Purushottam Kar


  Access Paper or Ask Questions

Supervised Learning with Similarity Functions


Oct 22, 2012
Purushottam Kar, Prateek Jain

* To appear in the proceedings of NIPS 2012, 30 pages 

  Access Paper or Ask Questions

Random Feature Maps for Dot Product Kernels


Mar 26, 2012
Purushottam Kar, Harish Karnick

* Journal of Machine Learning Research, W&CP 22 (2012) 583-591 
* To appear in the proceedings of the 15th International Conference on Artificial Intelligence and Statistics (AISTATS 2012). This version corrects a minor error with Lemma 10. Acknowledgements : Devanshu Bhimwal 

  Access Paper or Ask Questions

Similarity-based Learning via Data Driven Embeddings


Dec 22, 2011
Purushottam Kar, Prateek Jain

* To appear in the proceedings of NIPS 2011, 14 pages 

  Access Paper or Ask Questions

Random Projection Trees Revisited


Oct 20, 2010
Aman Dhesi, Purushottam Kar

* Accepted for publication at NIPS 2010. This version corrects an incorrect usage of the term Assouad dimension - acknowledgments : James Lee 

  Access Paper or Ask Questions