My general interests are very broad — I’m interested in AI, machine learning, programming languages, complexity theory, algorithms, security, quantum computing, you name it. However, I think that it is really important for us to build safe, aligned AI, and so my research focuses on addressing that. Currently, I am working on practical algorithms for inverse reinforcement learning that take into account the systematic cognitive biases that humans have.
In the past, I worked with Ras Bodik in the PLSE lab at the University of Washington. I applied program synthesis techniques to automatically generate incremental update rules that accelerated approximate sampling algorithms used in probabilistic programming. I have also applied partial evaluation and memoization to compile sampling algorithms.
I am currently supported by an NSF Fellowship, and was supported by a Berkeley Fellowship for my first two years in grad school.
- Rohin Shah, Rastislav Bodik. 2017. Automated Incrementalization through Synthesis. In Proceedings of the First Workshop on Incremental Computing (IC ’17).
- Rohin Shah, Emina Torlak, Rastislav Bodik. 2016. SIMPL: A DSL for Automatic Specialization of Inference Algorithms. arXiv:1604.04729.
- Phitchaya Mangpo Phothilimthana, Tikhon Jelvis, Rohin Shah, Nishant Totla, Sarah Chasins, and Rastislav Bodik. 2014. Chlorophyll: synthesis-aided compiler for low-power spatial architectures. In Proceedings of the 35th ACM SIGPLAN Conference on Programming Language Design and Implementation (PLDI ’14).
- PC Member, First Workshop on Incremental Computing (IC 2017)