Rishabh Iyer's Website

My photo

Welcome to my webpage

I am a Ph.D candidate at the University of Washington, Seattle and am working with Prof. Jeff Bilmes. I am currently doing an internship at the Machine Learning Group at Microsoft Research, Redmond and am working with Max Chickering and Chris Meek. In the summer of 2012, I did an internship at MSR, Redmond and worked with Dr. Matthai Phillipose at the Mobility and Networking Research Group. Prior to coming to UW, I spent four awesome years, at the Indian institute of Technology, Bombay where I completed my B.Tech in Electrical Engineering. At IIT Bombay, I worked with Prof. Subhasis Chaudhuri. I also did my internship an 2010 at the Computer Science Department at Simon Fraser University, where I worked with Prof. Torsten Möller. As an undergraduate, I worked mainly in computer vision and image processinge.

My research interests are at the intersection of Discrete optimization and Machine Learning, and am particularly interested in subset selection problems in machine learning like summarization, data subset selection, segmentation, feature selection, sensor placement, image correspondence etc. My work is focussed on a particular class of discrete optimization problems called Submodular Optimization, which on one hand are powerful, flexible and representable models in many real world applications, but on the other hand also admit algorithms with often strong theoretical guarantees. My work focusses on investigating certain theoretical characterizations of submodular functions and exploiting these in machine learning applications. One significant thread of my research revolves around providing faster, scalable and more practical algorithms for a large class of submodular optimization problems, and applying them to several real world problems. I am keenly interested in connecting theory with practice, and am hence investigating various applications of submodular optimization in computer vision, natural language processing, speech and information retrieval.

I recently received the Microsoft Research Fellowship award, which will support my research in the coming academic year! Thanks Microsoft! I also received the Facebook Fellowship award (declined in the favor of the Microsoft one), the Yang Outstanding Doctoral student award, and best paper awards at the top tier Machine Learning conferences, Neural Information Processing Systems (NIPS) and International Conference for Machine Learning (ICML). Here is a formal bio in third person.

For more information, please see some of my recent publications (DBLP, Google Scholar Profile), or contact me at rkiyer at u.washington.edu. Here is a link to my Curriculum Vitae.

I plan to graduate towards the end of this year (2014), and am actively looking for research positions, preferably in the Seattle area.


Conference Publications

(C9) Rishabh Iyer, Stefanie Jegelka and Jeff Bilmes, Monotone Closure of Relaxed Constraints in Submodular Optimization: Connections Between Minimization and Maximization, To appear In Uncertainity in Artificial Intelligence (UAI), Quebec City, Canada, July - 2014 PDF, Extended Version.

(C8) Kai Wei, Rishabh Iyer, and Jeff Bilmes, Fast Multi-stage Submodular Maximization, To appear In Proc. International Conference on Machine Learning (ICML), Beijing, China, June - 2014 PDF, Extended Version.

(C7) Rishabh Iyer and Jeff A. Bilmes, Submodular Optimization with Submodular Cover and Submodular Knapsack Constraints, In Advances of Neural Information Processing Systems (NIPS), Lake Tahoe, Nevada, December - 2013 PDF, Arxiv Extended Version, Slides, Video (Winner of the Outstanding paper award)

(C6) Rishabh Iyer, Stefanie Jegelka, and Jeff A. Bilmes, Curvature and Optimal Algorithms for Learning and Minimizing Submodular Functions, In Advances of Neural Information Processing Systems (NIPS), Lake Tahoe, Nevada, December - 2013 PDF, Arxiv Extended Version, Poster

(C5) Rishabh Iyer and Jeff A. Bilmes, The Lovasz-Bregman Divergence and connections to rank aggregation, clustering and web ranking , In Uncertainity in Artificial Intelligence (UAI), Bellevue, Washington, July - 2013 PDF, Extended Version, Slides (selected for oral presentation, 11% Acceptance rate).

(C4) Rishabh Iyer, Stefanie Jegelka, and Jeff A. Bilmes, Fast Semidifferential-based Submodular Function Optimization, In Proc. International Conference on Machine Learning (ICML), Atlanta, Georgia, June - 2013 PDF, Extended Version, Arxiv, Slides, Code, Video (Winner of the Best paper award).

(C3) Rishabh Iyer and Jeff A. Bilmes, Submodular-Bregman and the Lovasz-Bregman Divergences with Applications, In Advances of Neural Information Processing Systems (NIPS), Lake Tahoe, Nevada, December - 2012 PDF, Extended Version, Poster.

(C2) Rishabh Iyer and Jeff A. Bilmes, Algorithms for Approximate Minimization of the Difference between Submodular Functions, In Uncertainity in Artificial Intelligence (UAI), Catalina Islands, CA, August - 2012 PDF, Extended Version, Slides, Code (selected for oral presentation, 9% Acceptance rate).

(C1) Shah Ronak, Rishabh Iyer and Subhasis Chaudhuri, Object Mining for Large Video Data, In Proc. British Machine Vision Conference (BMVC), Dundee, Scotland, United Kingdom, August - 2011, PDF (selected for oral presentation - 8% Acceptance rate).

Workshops and Preprints

(W2) Rishabh Iyer, Stefanie Jegelka and Jeff A. Bilmes, Mirror Descent-Like Algorithms for Submodular Optimization, In Advances of Neural Information Processing Systems (NIPS) Workshop on Discrete Optimization in Machine Learning (DISCML): Structure and Scalability, Lake Tahoe, Nevada, December - 2012 PDF, Poster.

(P1) Rishabh Iyer, Rushikesh Borse, Shah Ronak and Subhasis Chaudhuri, Embedding Capacity estimation for pixel pair based watermarking schemes, Arxiv Preprint.

(W1) Rishabh Iyer and Torsten Möller, A spatial domain optimization for sampling pointsets, MITACS Globalink Research Symposium, University of British Columbia, Canada - 2010. PDF

Professional Activities

Reviewer: ICML 2013/2014, NIPS 2013/2014.

Collaborators (Past and Present)

Jeff Bilmes, Stefanie Jegelka, Yoshinobu Kawahara, Kai Wei, Sebastian Tschiatschek, Ganesh Ramakrishnan, Matthai Phillipose, Bethany Herwaldt, Subhasis Chaudhuri, Torsten Möller.

Talks

(T6) Submodular Combinatorial Problems in Machine Learning: Algorithms and Applications, Invited Talk at IIT Bombay, IISc Bangalore, MSR Bangalore, IIT Gandhinagar, TOPS Seminar (UW), Yahoo! Machine Learning Lunch (UW) (See related video)

(T5) Submodular Optimization with Submodular Cover and Submodular Knapsack Constraints, NIPS-2013, Lake Tahoe, Dec 2013. (see video of this talk)

(T4) The Lovasz-Bregman Divergence and connections to rank aggregation, clustering and web ranking, UAI-2013, Bellevue, July 2013.

(T3) Fast Semidifferential-based Submodular Function Optimization, ICML-2013, Atlanta, June 2013. (see video of this talk)

(T2) Submodular Bregman divergences and Lovasz-Bregman divergences with Applications to Machine Learning, Seminar, IIT Bombay, March 2013.

(T1) Algorithms for Approximate Minimization of the Difference between Submodular Functions, UAI-2012, Catalina Island, August 2012.

Fun Stuff

My hobies include biking, hiking, sports (particularly squash), cooking, meditation, and philosophical discussions. On weekends, I love to volunteer at the Vedic Cultural Center, Sammamish. I am strong advocate of work-life balance!
You can find me on facebook, LinkedIn and Google.
Finally this is the person I owe my life to!