Publications

  • Shiv Kumar Tavker, Harish G. Ramaswamy and Harikrishna Narasimhan. Consistent Plug-in Classifiers for Complex Objectives and Constraints. In Neural Information Processing Systems (NeurIPS), 2020.

  • Mingyan Zhang, Harish G. Ramaswamy and Shivani Agarwal. Convex Calibrated Surrogates for the Multi-Label F-Measure. In International Conference on Machine Learning (ICML), 2020.

  • Saurabh Desai and Harish G. Ramaswamy. Ablation-CAM: Visual Explanations for Deep Convolutional Network via Gradient-free Localization. IEEE Winter Conference on Applications of Computer Vision (WACV) 2020. (Best paper winner)

  • Siddhartha Arora, Mitesh M. Khapra, Harish G. Ramaswamy. On Knowledge Distillation from Complex Networks for Response Prediction. NAACL 2019.

  • Anirban Laha, Saneem A Chemmangath, Priyanka Agrawal, Mitesh M. Khapra, Karthik Sankaranarayanan, Harish G. Ramaswamy. On controllable alternatives to Sparsemax. In Neural Information Processing Systems (NIPS), 2018.

  • Harish G. Ramaswamy, Ambuj Tewari, and Shivani Agarwal. Consistent Algorithms for Multiclass Classification Problems with an abstain Option. Electronic Journal of Statistics, 2018. [link]

  • Harish G. Ramaswamy, Clayton Scott and Ambuj Tewari, Mixture Proportion Estimation via Kernel Embeddings of Distributions. In International Conference on Machine Learning (ICML), 2016. [link]

  • Harish G. Ramaswamy and Shivani Agarwal. Convex Calibration Dimension for Multiclass Loss Matrices. Journal of Machine Learning Research (JMLR) 2016. [link]

  • Weiwei Pan, Harikrishna Narasimhan, Purushottam Kar, Pavlos Protopapas, and Harish G. Ramaswamy. Optimizing the Multi-class F-measure via Biconcave Programming. International Conference on Data Mining (ICDM), 2016.

  • Harish G. Ramaswamy, Ambuj Tewari, and Shivani Agarwal. Convex Calibrated Surrogates for Hierarchical Classification. In International Conference on Machine Learning (ICML), 2015. [link]

  • Harikrishna Narasimhan*, Harish G. Ramaswamy*, Aadirupa Saha and Shivani Agarwal. Consistent Multiclass Algorithms for Complex Performance Measures. In International Conference on Machine Learning (ICML), 2015. [link]

  • Harish G. Ramaswamy, Balaji S. Babu, Shivani Agarwal and Robert C. Williamson. On the Consistency of Output Code Based Learning Algorithms for Multiclass Learning Problems. In Conference on Learning Theory (COLT), 2014. [link]

  • Harish G. Ramaswamy, Shivani Agarwal and Ambuj Tewari. Convex Calibrated Surrogates for Low-Rank Loss Matrices with Applications to Subset Ranking Losses. In Neural Information Processing Systems (NIPS), 2013. [link]

  • Harish G. Ramaswamy and Shivani Agarwal. Classification Calibration Dimension for General Multiclass Losses. In Neural Information Processing Systems (NIPS), 2012. [link]



Thesis:

Design and Analysis of Consistent Algorithms for Multiclass Learning Problems. PhD Thesis, Indian Institute of Science, Bengaluru. June 2015. [link]