As a follow up to Memorize, I worked with Manuel Gomez-Rodriguez and the creators of Swift Learning App, Christoph Moser and Graham Lancashire, to design a new algorithm for scheduling lessons Select. We ran large scale randomized experiments to verify that the learning indeed was improved by using the ML based instructions.

• "Large-scale randomized experiment reveals machine learning helps people learn and remember more effectively" ~ Nature Science of Learning (2021); Open Access Paper.
• A #BehindThePaper blog post.
• Networks-Learning/spaced-selection

My contributions to the sparse matrix API were recognized by making me a co-contributor and co-author to the Nature Methods paper describing SciPy, which coincided with the release of version 1.0 of the library. Also, this along with my contribution to python/cpython, i.e. the Python programming language, also earned me a badge on GitHub for contributing to the Mars 2020 Helicopter Contributor. I always wanted to put something in space 🤗

• "SciPy 1.0: fundamental algorithms for scientific computing in Python" ~ Nature Methods (2020); Paper.
• "Utkarsh Upadhyay contributed code to 2 repositories used in the Mars 2020 Helicopter Mission: python/cpython, and scipy/scipy." ~ GitHub

With Róbert Busa-Fekete, Wojciech Kotłowski, Dávid Pál, and Balázs Szörényi, I have looked at hte problem of learning to optimally web-crawl pages while simultaneously learning how often they change. Our conclusions about the properties of the learning algorithm and results about learnability of rates of Poisson processes with partial observability apply to many other problems and scenarios as well. We provide the first sub-linear guarantees for such problems and take the first step in the direction of establishing that given some constraints on the optimization problems (e.g. RedQueen, Memorize) which schedule events in continuous time, learning the rates/parameters of the environment while simultaneously optimizing is possible with zero-regret.

• "Learning to Crawl" ~ AAAI (2020); Paper.

With Abir De, Aasish Pappu, and Manuel Gomez-Rodriguez, I have uncovered a connection between complexity of online discussions and the notion of sign-rank of matrices. This allows us to determine the complexity of online discussions just by looking at the pattern of upvotes/downvotes cast by users on others' comments; the key insight is using humans as oracles and by-passing the nuances of sarcasm and humor often present in online comments.

• "On Complexity of Opinions and Online Discussions" ~ WSDM (2019); Paper.
• Networks-Learning/discussion-complexity

With Abir De and Manuel Gomez-Rodriguez, I have developed a deep reinforcement learning algorithm for controlling agents whose actions are performed, and who receives feedback from the environment, at discrete localized points in continuous real time. This is in contract to the classical RL setup where the actions and rewards (feedback) are synchronously given to the agent at discrete points in time.

• "Deep Reinforcement Learning of Marked Temporal Point Processes" ~ NeurIPS (2018); Paper.
• Networks-Learning/tpprl
• 3-minute video summary

With Behzad Tabibian, Abir De, Ali Zarezade, Bernhard Schölkopf and Manuel Gomez-Rodriguez, I have determined the optimal reviewing schedule to keep knowledge fresh in your memory for optimal recall while minimizing effort spent on learning it.

• "Enhancing human learning via spaced repetition optimization" ~ PNAS (2019); Paper.
• Networks-Learning/memorize
• Webpage with summary

With Ali Zarezade, and Manuel Gomez-Rodriguez, I discovered a simple algorithm for keeping your posts visible on your follower's feeds.

• "RedQueen: An Online Algorithm for Smart Broadcasting in Social Networks" Oral presentation at WSDM (2017); Paper.
• Webpage with demo
• Networks-Learning/RedQueen

With Isabel Valera and Manuel Gomez-Rodriguez, I am developing models to understand how learning happens on Crowdlearning sites, such as Stack Overflow and Wikipedia.

• "On Crowdlearning: How do People Learn in the Wild?", oral presentation at Workshop on Machine Learning for Education at NeurIPS (2016);
• "Uncovering the dynamics of Crowdlearning and the Value of Knowledge", oral presentation at WSDM (2017); Paper.

With Nan Du, Hanjun Dai, Rakshit Trivedis, Manuel Gomez-Rodriguez, and Le Song, I developed am model which uses recurrent neural networks to model point processes, yielding impressive predictive results.

• "Recurrent marked temporal point processes: Embedding event history to vector", Poster presetned at KDD (2016); Paper.

• Slides for the tutorial
• Project material on Github