I am an Assistant Professor in the Computer Science Department at Carnegie Mellon University. I am also affiliated with the Machine Learning Department.

I work broadly in machine learning and my goal is to make machine learning more reliable and robust. My work spans both theory and practice, and leverages tools and concepts from statistics, convex optimization, and algorithms to improve the robustness of modern systems based on deep learning.

My group's research is generously supported by an AI2050 Early Career Fellowship from Schmidt Futures, Apple, Google, and Open Philanthropy.

Until recently, I was a postdoc at Berkeley AI Research. I received my PhD from Stanford University in 2021 where I was fortunate to be advised by Percy Liang. My thesis won the Arthur Samuel Best Thesis award at Stanford. Previously, I obtained my BTech in Computer Science from IIT Madras in 2016.

If you are a current CMU undergraduate or masters student interested in working with my group, please apply here .

Preprints

Publications

PhD advisees

Undergraduate advisees

  • Suhas Kotha (CMU)
  • Jhih-Yi Hseih (CMU; co-advised with Nihar Shah)
  • Raashi Mohan (CMU)
I am fortunate to also collaborate with several masters students and PhD students at CMU who I do not directly advise.

Workshops

  • Workshop on robustness of zero/few-shot learning in foundation models (R0-FoMo), NeurIPS 2023 (upcoming)
  • Mathematics of Modern Machine Learning (M3L), NeurIPS 2023 (upcoming)
  • Workshop on Formal Verification of Machine Learning , ICML 2022
  • Robust and reliable machine learning in the real world, ICLR 2021

Tutorials

Selected recent talks

Email: raditi'at'cmu.edu

Office: GHC 7005