Harikrishna Narasimhan (ஹரிகிருஷ்ணா நரசிம்மன்)


I have been a post-doctoral researcher at IACS, Harvard University since September 2015, working with David C. Parkes. You can contact me at h__________@seas.harvard.edu (please replace the dashes with my last name). 

I completed my PhD in computer science at the Indian Institute of Science (IISc), Bangalore, working with Shivani Agarwal, and supported by the Google India PhD Fellowship in Machine Learning. I spent the fall of 2014 visiting Harvard, working with David Parkes, and in the summer of 2014, I interned at Microsoft Research, Bangalore with Prateek Jain. Prior to joining PhD, I completed my masters in computer science from IISc, and bachelors in computer science from College of Engineering, Anna University, Chennai.

My research interests broadly lie in the areas of machine learning, statistical learning theory, and optimization, and their intersection with microeconomics and the social sciences. The following are some themes that I am excited about:

  • Algorithms and theory for learning problems with complex evaluation requirements
  • Ranking and structured prediction problems
  • Interface between machine learning and mechanism design

You can find my resume here.


Publications and Preprints

Dutting, P., Feng, Z., Narasimhan, H. and Parkes, D.C. 'Optimal Auctions through Deep Learning'. arXiv:1706.03459 [cs.GT], 2017.

Narasimhan, H. and Agarwal, S. 'Support Vector Algorithms for Optimizing the Partial Area Under the ROC Curve'. Neural Computation, 2017, To appear. 

Pan, W., Narasimhan, H., Kar, P., Protopapas, P. and Ramaswamy, H. 'Optimizing the Multiclass F-measure via Biconcave Programming'. In Proceedings of the IEEE International Conference on Data Mining (ICDM), 2016.

Li, S., Kar, P.K., Narasimhan, H., Chawla, S. and Sebastiani, F. 'Stochastic Optimization Techniques for Quantification Performance Measures'.  In Proceedings of the 22nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2016.

Narasimhan, H., and Parkes, D.C. 'A General Statistical Framework for Designing Strategy-proof Assignment Mechanisms'. In Proceedings of the Conference on Uncertainty in Artificial Intelligence (UAI), 2016. 

Narasimhan, H., Agarwal, S. and Parkes, D.C. 'Automated Mechanism Design without Money via Machine Learning'. In Proceedings of the 25th International Joint Conference on Artificial Intelligence (IJCAI), 2016.

Majumder, B., Baraneedharan, U., Thiyagarajan, S., Radhakrishnan, P., Narasimhan, H., Dhandapani, M., Brijwani, N., Pinto, D.D., Prasath, A., Shanthappa, B.U., Thayakumar, A., Surendran, R., Babu, G., Shenoy, A.M., Kuriakose, M.A., Bergthold, G., Horowitz, P., Loda, M., Beroukhim, R., Agarwal, S., Sengupta, S., Sundaram, M. and Majumder, P.K. 'Predicting clinical response to anticancer drugs using an ex vivo platform that captures tumour heterogeneity'. Nature Communications, 6:6169, 2015.
[paper] [Featured in Business Wire, Genome Web, CIO, The Telegraph]

Narasimhan, H., Parkes, D.C. and Singer, Y. 'Learnability of influence in networks'. In Advances in Neural Information Processing Systems (NIPS), 2015.

Ahmed, S., Narasimhan, H. and Agarwal, S. 'Bayes optimal feature selection for supervised learning with general performance measures'. In Proceedings of the 31st Conference on Uncertainty in Artificial Intelligence (UAI), 2015.

Narasimhan, H.*, Ramaswamy, H. G.*, Saha, A. and Agarwal, S. 'Consistent multiclass algorithms for complex performance measures'. In Proceedings of the 32nd International Conference on Machine Learning (ICML), 2015.
(*both authors contributed equally to the paper)

Narasimhan, H., Kar, P., and Jain, P. 'Optimizing non-decomposable performance measures: A tale of two classes'. In Proceedings of the 32nd International Conference on Machine Learning (ICML), 2015.

Kar, P., Narasimhan, H., and Jain, P. 'Surrogate functions for maximizing precision at the top'. In Proceedings of the 32nd International Conference on Machine Learning (ICML), 2015.
[slides by Purushottam] [poster by Purushottam]

Narasimhan, H.*, Vaish, R.* and Agarwal, S., 'On the statistical consistency of plug-in classifiers for non-decomposable performance measures'. In Advances in Neural Information Processing Systems (NIPS), 2014.
[paper] [poster]   (*both authors contributed equally to the paper)

Kar, P., Narasimhan, H., and Jain, P. 'Online and stochastic gradient methods for non-decomposable loss functions'. In Advances in Neural Information Processing Systems (NIPS), 2014.
[paper] [poster by Purushottam]

Saha, A., Dewangan, C., Narasimhan, H., Sriram, S., and Agarwal, S. 'Learning score systems for patient mortality prediction in intensive care units via orthogonal matching pursuit'. In Proceedings of the 13th International Conference on Machine Learning and Applications (ICMLA), 2014.
[paper] [slides] [poster at NIPS14 MLCHG]

Agarwal, A., Narasimhan, H., Kalyanakrishnan, S. and Agarwal, S., 'GEV-canonical regression for accurate binary class probability estimation when one class is rare'. In Proceedings of the 31st International Conference on Machine Learning (ICML), 2014.
[paper] [slides by Arpit] [poster by Arpit]

Narasimhan, H. and Agarwal, S., 'On the relationship between binary classification, bipartite ranking, and binary class probability estimation'. In Advances in Neural Information Processing Systems (NIPS), 2013.
[paper] [spotlight-slides][video]

Narasimhan, H. and Agarwal, S., 'SVM_pAUC^tight: A new support vector method for optimizing partial AUC based on a tight convex upper bound'. In Proceedings of the 19th ACM SIGKDD Conference on Knowledge, Discovery and Data Mining (KDD), 2013.
[paper] [code] [slides] [poster]

Menon, A. K., Narasimhan, H., Agarwal, S. and Chawla, S., 'On the statistical consistency of algorithms for binary classification under class imbalance'. In Proceedings of the 30th International Conference on Machine Learning (ICML), 2013.
[paper] [spotlight-slides] [poster] [video]

Narasimhan, H. and Agarwal, S., 'A structural SVM based approach for optimizing partial AUC'. In Proceedings of the 30th International Conference on Machine Learning (ICML), 2013.
[paper] [suppl. material] [code] [slides] [poster] [video]


Awards and Honors

  • Awarded student travel/volunteer scholarship for ICML 2015, NIPS 2014, NIPS 2013, ICML 2013 and KDD 2013.
  • Awarded Shell India Computational Talent Prize 2013 (SICTP) Gold Award.
  • Awarded Google India PhD Fellowship in Machine Learning, 2013.
  • Awarded Computer Society of India (Bangalore Chapter) Medal for best ME student in computer science, 2013.
  • Secured an All India Rank of 4 (out of around 100,000) in GATE 2010.
  • Awarded Gold Medal for first rank in the bachelors programmer.
  • Several Awards during the bachelors programme for academic excellence including one for Best Outgoing Student.
  • Awarded a Certificate of Merit from South Indian Chamber of Commerce and Industry (SICCI) for best student in computer science (Anna University), 2011.

Teaching Assistance

Harvard CS 209b - Data Science 2 (Spring 2017)
Harvard CS 209a - Data Science 1 (Fall 2016) 
Harvard AC297r CSE Capstone Project (Spring 2016)
IISc E0 270 Machine Learning (Spring 2015) 
IISc E0 270 Machine Learning (Spring 2013) 
(Notes that I prepared for a 3-part tutorial on optimization: part 1, part 2, part 3.)
Subpages (1): Untitled