Arpit Agarwal PhD Student Department of Computer & Information Science University of Pennsylvania Link to: CV (last updated: May 2018)

About Me

I am a fourth year PhD student in the Department of Computer & Information Science, at University of Pennsylvania, working with Prof. Shivani Agarwal. Before coming to Penn, I was a PhD student at CSA department, Indian Institute of Science. I completed masters in computer science and engineering at Indian Institute of Science.

I spent time visiting Prof. David Parkes at Harvard in Fall 2015, working on the problem of multi-task peer prediction.

My research interests broadly lie in the areas of Machine Learning, Learning Theory and Information Elicitation. Recently, I have been interested at problems on the interface of ranking and crowdsourcing.

Publications

• Stochastic Submodular Cover with Limited Adaptivity.
  Arpit Agarwal, Sepehr Assadi, and Sanjeev Khanna.
  SODA 2019 (To appear).
  


• Accelerated Spectral Ranking.
  Arpit Agarwal, Prathamesh Patil, and Shivani Agarwal.
  ICML 2018. [paper]
  


• Learning with Limited Rounds of Adaptivity: Coin Tossing, Multi-Armed Bandits, and Ranking from Pairwise Comparisons.
  Arpit Agarwal, Shivani Agarwal, Sepehr Assadi, and Sanjeev Khanna.
  COLT 2017. [paper]
  


• Peer Prediction with Heterogeneous Users.
  Arpit Agarwal, Debmalya Mandal, David Parkes, and Nisarg Shah.
  EC 2017. [paper]
  


• Informed Truthfulness in Multi-Task Peer Prediction.
  Victor Shnayder, Arpit Agarwal, Rafael Frongillo, and David C. Parkes.
  EC 2016. [arXiv]
  


• On Consistent Surrogate Risk Minimization and Property Elicitation.
  Arpit Agarwal and Shivani Agarwal.
  COLT 2015. [paper]
  
  
• GEV-Canonical Regression for Accurate Binary Class Probability Estimation when One Class is Rare.
  Arpit Agarwal, Harikrishna Narasimhan, Shivaram Kalyanakrishnan and Shivani Agarwal.
  ICML 2014. [paper] [slides]
  

Recent Talks

• Accelerated Spectral Ranking.
  International Conference on Machine Learning, Stockholm, July 2017 .
  Google Research New York, September 2017.
  


• Learning with Limited Rounds of Adaptivity: Coin Tossing, Multi-Armed Bandits, and Ranking from Pairwise Comparisons.
  Conference on Learning Theory, Amsterdam, July 2017
  Microsoft Research Bangalore, July 2017.
  Indian Institute of Science, Bangalore, July 2017.
  


• On Consistent Surrogate Risk Minimization and Property Elicitation.
  ACM IKDD Conference on Data Science (CoDS), Pune, March 2016.
  


• Connections between Calibrated Surrogates in Supervised Learning and Property Elicitation in Probability Forecasting.
  Harvard EconCS group meeting, December 2015.
  


• GEV-Canonical Regression for Accurate Binary Class Probability Estimation when One Class is Rare.
  International Conference on Machine Learning (ICML), Beijing, June 2014.
  


• Randomization at work: An introduction to Randomized Algorithms.
  CSA Undergraduate Summer School, June 2013.
  

Graduate Courses

Organizational Activities

• Member of Departmental Curriculum Committee, CSA, IISc, 2015-2016.
• Lead volunteer for Big Data Initiative, CSA, IISc, 2014.
• Volunteer for Indo-US Lectures Week in Machine Learning, Game Theory and Optimization, 2014.
• Organizer of machine learning programming contest TagMe! in CSA Open Days, Indian Institute of Science, 2014.

Misc

• I am organized a reading group on Optimization in the summer of 2016.
• In my free time I enjoy running or debating on Indian politics and history.