Gaurav Arya

I'm a second-year PhD student in the Computer Science Department at CMU, advised by Feras Saad. My research develops principled programming language techniques that enable the design and practice of new statistical methods.

In my undergraduate at MIT, I did research with the Nanostructures and Computation Group, the Julia Lab, and the Probabilistic Computing Project. For leisure, I enjoy playing tennis, reading, and birding.

Email  /  GitHub  /  Google Scholar

Papers

• GradInf: Gradient Estimation as Probabilistic Inference
  Gaurav Arya, Mathieu Huot, Moritz Schauer, Alexander K. Lew, Feras Saad
  PLDI, Proceedings of the ACM on Programming Languages (10), 2026
  bibtex /
• End-to-End Metasurface Design for Temperature Imaging via Broadband Planck-Radiation Regression
  Sophie Fisher, Gaurav Arya, Arka Majumdar, Zin Lin, Steven G. Johnson
  Advanced Optical Materials, 13(9), 2025
  arXiv / paper / bibtex /
• Automatic Bayesian Inference of Reaction Networks via Guiding
  Gaurav Arya
  Master's Thesis, Massachusetts Institute of Technology, 2024
  thesis / bibtex /
• Gradient Estimation via Differentiable Metropolis-Hastings
  Gaurav Arya*, Moritz Schauer*, Ruben Seyer*
  arXiv:2406.14451 [math.ST], 2024
  arXiv / bibtex /
• End-to-End Optimization of Metasurfaces for Imaging with Compressed Sensing
  Gaurav Arya, William F. Li, Charles Roques-Carmes, Marin Soljačić, Steven G. Johnson, Zin Lin
  ACS Photonics, Vol. 11, Issue 5, 2024
  arXiv / paper / code / bibtex /
• Transcending Shift-Invariance in the Paraxial Regime via End-to-End Inverse Design of Freeform Nanophotonics
  William F. Li, Gaurav Arya, Charles Roques-Carmes, Zin Lin, Steven G. Johnson, Marin Soljačić
  Optics Express, Vol. 31, Issue 15, 2023
  arXiv / paper / bibtex /
• Differentiating Metropolis-Hastings to Optimize Intractable Densities
  Gaurav Arya*, Ruben Seyer*, Frank Schäfer, Kartik Chandra, Alexander K. Lew, Mathieu Huot, Vikash Mansinghka, Jonathan Ragan-Kelley, Chris Rackauckas, Moritz Schauer
  ICML 2023 Workshop on Differentiable Almost Everything: Differentiable Relaxations, Algorithms, Operators, and Simulators
  arXiv / code / bibtex /
• Automatic Differentiation of Programs with Discrete Randomness
  Gaurav Arya, Moritz Schauer, Frank Schäfer, Chris Rackauckas
  NeurIPS, Proceedings of the 36th Conference on Neural Information Processing Systems, 2022
  arXiv / paper / code library / code docs / bibtex /