I’m a PhD student in Computer Science studying machine learning with Joan Bruna in the CILVR Lab at the Courant Institute at NYU. I am interested in scalable and efficient learning for decision making problems. Recently I have been mostly working in the offline reinforcement learning setting, trying to understand when and how we can learn effective policies from fixed datasets. I have also worked on provable guarantees for reinforcement learning with function approximation and am interested in representation learning, transfer learning, and the generalization and optimization of neural networks.
My work is supported by an NDSEG fellowship. I’ve interned at MSR in virtual Montreal working with Romain Laroche and Remi Tachet des Combes on offline RL and at FAIR in Paris working with Alessandro Lazaric and Matteo Pirotta on efficient exploration. And I did my undergrad at Yale where I double majored in Math and Computer Science where my various advisors were Andrew Barron, Dana Angluin, John Murray, and Pat Devlin.
Feel free to email me at