Dr. Rishabh Iyer

Assistant Professor

Degrees:

• Post-Doctoral Researcher, University of Washington, 2016
• Ph.D. in Computer Science, University of Washington, Seattle, 2015
• B.Tech, IIT-Bombay, 2011

Research Interests:

• Artificial Intelligence
• Machine Learning
• Discrete Optimization (specifically submodular optimization) in Machine Learning
• Convex and Non-Convex Optimization in Machine Learning
• Deep Learning for Image Classification and Object Detection
• Data Summarization (Video/Image/Text)
• Active Learning, Data Subset Selection, Data partitioning, Model Compression/Pruning, etc.
• Video Analytics
• Online Learning, Contextual Bandits and Reinforcement Learning.
• Click Prediction, Web Search and Information Retrieval.

Major Honors and Awards:

• Selected as a finalist in the LDV Computer Vision Conference, New York in 2017
• Yang Outstanding Graduate Student Award, University of Washington, Seattle
• Microsoft Research Fellowship Award, 2014
• Facebook Fellowship Award, 2014 (Declined in favor of Microsoft)
• Best Paper Award at the International Conference of Machine Learning, 2013
• Best Paper Award at the Neural Information Processing Systems Conference, 2013
• Invited for Talks/Tutorials at the AMS Sectional Meeting, the International Symposium for Mathematical Programming (ISMP), 7^th IEEE Winter Conference on Applications of Computer Vision (WACV), and Non-Convex Optimization and Machine Learning (NOML at IIT Bombay)

Representative Publications:

• Suraj Kothawade; Nathan Beck; Krishnateja Killamsetty; Rishabh Iyer, SIMILAR: Submodular Information Measures Based Active Learning In Realistic Scenarios,To Appear In Neural Information Processing Systems, NeurIPS 2021
• Krishnateja Killamsetty, Xujiang Zhou, Feng Chen, and Rishabh Iyer, RETRIEVE: Coreset Selection for Efficient and Robust Semi-Supervised Learning, To Appear In Neural Information Processing Systems, NeurIPS 2021
• Ping Zhang, Rishabh K Iyer, Ashish V. Tendulkar, Gaurav Aggarwal, Abir De, Learning to Select Exogenous Events for Marked Temporal Point Process, To Appear In Neural Information Processing Systems, NeurIPS 2021
• Krishnateja Killamsetty, Durga Sivasubramanian, Ganesh Ramakrishnan, Abir De, Rishabh Iyer, GRAD-MATCH: A Gradient Matching Based Data Subset Selection for Efficient Deep Model Training, The Thirty-eighth International Conference on Machine Learning, ICML 2021
• Durga Sivasubramanian, Rishabh Iyer, Ganesh Ramakrishnan, and Abir De, Training Data Subset Selection for Regression with Controlled Validation Error, The Thirty-eighth International Conference on Machine Learning, ICML 2021
•  Krishnateja Killamsetty, S Durga, Ganesh Ramakrishnan, and Rishabh Iyer, GLISTER: Generalization based Data Subset Selection for Efficient and Robust Learning, 35th AAAI Conference on Artificial Intelligence, AAAI 2021
•  Rishabh Iyer, Ninad Khargonkar, Jeff Bilmes, and Himanshu Asnani, Submodular Combinatorial Information Measures with Applications in Machine Learning, The 32nd International Conference on Algorithmic Learning Theory, ALT 2021
• Rishabh Iyer and Jeff Bilmes, A Memoization Framework for Scaling Submodular Optimization to Large Scale Problems, To Appear in Artificial Intelligence and Statistics (AISTATS) 2019, Naha, Okinawa, Japan
• Vishal Kaushal, Rishabh Iyer, Suraj Kothiwade, Rohan Mahadev, Khoshrav Doctor, and Ganesh Ramakrishnan, Learning From Less Data: A Unified Data Subset Selection and Active Learning Framework for Computer Vision, 7th IEEE Winter Conference on Applications of Computer Vision (WACV), 2019 Hawaii, USA (Link to the Video)
• Wenruo Bai, Rishabh Iyer, Kai Wei, Jeff Bilmes, Algorithms for optimizing the ratio of submodular functions, In Proc. International Conference on Machine Learning( ICML) 2016 (Link to Video)
• Kai Wei, Rishabh Iyer, Shenjie Wang, Wenruo Bai, Jeff Bilmes, Mixed robust/average submodular partitioning: Fast algorithms, guarantees, and applications, In Advances of Neural Information Processing Systems (NIPS) 2015
• Kai Wei, Rishabh Iyer, Jeff Bilmes, Submodularity in data subset selection and active learning, International Conference on Machine Learning (ICML) 2015
• Rishabh Iyer and Jeff Bilmes, Submodular optimization with submodular cover and submodular knapsack constraints, In Advances Neural Information Processing Systems 2013 (Winner of the Outstanding Paper Award) Link to Video, from 56th Minute.
• Rishabh Iyer, Stefanie Jegelka, Jeff Bilmes, Fast semidifferential-based submodular function optimization, International Conference on Machine Learning (ICML) 2013 (Winner of the Best Paper Award) Link to Video

Notable Service:

• Reviewer for Journal of Machine Learning Research (JMLR 2016, 2017, 2018)
• Reviewer for Journal of Discrete Applied Mathematics (DAM 2016)
• Reviewer for Pattern Analysis and Machine Intelligence (PAMI 2015, 2016, 2017)
• Reviewer for Symposium of Discrete Algorithms, SODA 2019
• Reviewer for Conference on Learning Theory (COLT) 2019
• Reviewer for International Conference of Machine Learning (ICML) 2013 – 2019
• Reviewer for Neural Information Processing Systems (NIPS) 2013 – 2019
• Program Committee Member for Uncertainty in Artificial Intelligence (UAI) 2013 – 2016
• Program Committee Member for American Association of Artificial Intelligence (AAAI) 2016 – 2018
• Program Committee Member for Artificial Intelligence and Statistics (AISTATS) 2016 – 2019
• Reviewer for International Conference of Learning Representations (ICLR) 2018, 2019