Aditya Grover

I am a fourth-year Ph.D candidate in Computer Science at Stanford University, affiliated with the Artificial Intelligence Laboratory and the Statistical Machine Learning Group. My advisor is Stefano Ermon.

I am interested in developing algorithms for efficient learning and inference in probabilistic models. A large part of my research focus in this direction entails the design and analysis of suitable learning objectives (AAAI 2018), improving algorithms for stochastic optimization via approximate inference and uncertainty quantification (AISTATS 2018), and grounding such learning frameworks for applications across machine learning e.g., multiagent reinforcement learning, compressed sensing, and constraint satisfaction (ICML 2018, NIPS 2018).

My research is supported by a Microsoft Research PhD Fellowship in machine learning and a Stanford Data Science Scholarship. In the course of my Ph.D, I have spent two summers interning at OpenAI (2017) and MSR, Redmond (2018). Before joining Stanford, I obtained my bachelors in Computer Science and Engineering from IIT Delhi in 2015.

Recent

• December 2018: Co-organizing a workshop on Relational Representation Learning at NIPS 2018
• Fall 2018: Co-instructor for CS 236, a new class on Deep Generative Models at Stanford University
• July 2018: Presented a tutorial on Deep Generative Models at IJCAI 2018

Conference Publications

• Streamlining Variational Inference for Constraint Satisfaction Problems
  Aditya Grover, Tudor Achim, Stefano Ermon
  Advances in Neural Information Processing Systems (NIPS), 2018. To appear.


• Learning Policy Representations in Multiagent Systems
  Aditya Grover, Maruan Al-Shedivat, Jayesh K. Gupta, Yura Burda, Harrison Edwards
  International Conference on Machine Learning (ICML), 2018.
  [paper]
  Full Oral Presentation [acceptance rate: 212/2473 (8.6%)]


• Modeling Sparse Deviations for Compressed Sensing using Generative Models
  Manik Dhar, Aditya Grover, Stefano Ermon
  International Conference on Machine Learning (ICML), 2018.
  [paper] [code]
  Full Oral Presentation [acceptance rate: 212/2473 (8.6%)]


• Evaluating Generalization in Multiagent Systems using Agent-Interaction Graphs (short)
  Aditya Grover, Maruan Al-Shedivat, Jayesh K. Gupta, Yura Burda, Harrison Edwards
  International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2018.
  [paper]


• Variational Rejection Sampling
  Aditya Grover*, Ramki Gummadi*, Miguel Lazaro-Gredilla, Dale Schuurmans, Stefano Ermon
  International Conference on Artificial Intelligence and Statistics (AISTATS), 2018.
  [paper][blog]


• Best arm identification in multi-armed bandits with delayed feedback
  Aditya Grover, Todor Markov, Peter Attia, Norman Jin, Nicholas Perkins, Bryan Cheong, Michael Chen, Zi Yang, Stephen Harris, William Chueh, Stefano Ermon
  International Conference on Artificial Intelligence and Statistics (AISTATS), 2018.
  [paper][code]


• Flow-GAN: Combining Maximum Likelihood and Adversarial Learning in Generative Models
  Aditya Grover, Manik Dhar, Stefano Ermon
  AAAI Conference on Artificial Intelligence (AAAI), 2018.
  [paper][code][blog]
  Full Oral Presentation [acceptance rate: 417/3800 (10.9%)]


• Boosted Generative Models
  Aditya Grover, Stefano Ermon
  AAAI Conference on Artificial Intelligence (AAAI), 2018.
  [paper][code]


• Variational Bayes on Monte Carlo Steroids
  Aditya Grover, Stefano Ermon
  Advances in Neural Information Processing Systems (NIPS), 2016.
  [paper][spotlight video]


• node2vec: Scalable Feature Learning for Networks
  Aditya Grover, Jure Leskovec
  Knowledge Discovery and Data Mining (KDD), 2016.
  [paper][code]
  Oral Plenary Presentation [acceptance rate: 70/784 (8.9%)]


• Contextual Symmetries in Probabilistic Graphical Models
  Ankit Anand, Aditya Grover, Mausam, Parag Singla
  International Joint Conference on Artificial Intelligence (IJCAI), 2016.
  [paper][code]
  Best Paper Award at the International Workshop on Statistical Relational AI (StarAI), 2016.


• A Deep Hybrid Model for Weather Forecasting
  Aditya Grover, Ashish Kapoor, Eric Horvitz
  Knowledge Discovery and Data Mining (KDD), 2015.
  [paper][press Microsoft , Gizmodo]


• ASAP-UCT: Abstraction of State-Action Pairs in UCT
  Ankit Anand, Aditya Grover, Mausam, Parag Singla
  International Joint Conference on Artificial Intelligence (IJCAI), 2015. [paper][code]


• A Novel Abstraction Framework for Online Planning (short)
  Ankit Anand, Aditya Grover, Mausam, Parag Singla
  International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2015.
  [paper]