profile_picture
Adhi Saravanan
Ph.D. Candidate (StatML CDT), University of Oxford
adhithya.saravanan@stats.ox.ac.uk

Hey! I am a first-year StatML PhD student at the University of Oxford, where I am advised by Yee Whye Teh and Tom Rainforth within OxCSML. I am broadly interested in robust machine learning, particularly generative modelling, and efficient data-acquisition, as well as in applying these methods in scientific applications.

Before coming to Oxford, I completed an integrated Masters in Computer and Information Engineering at the University of Cambridge, where I did my disseration on sound certification of Bayesian Neural Networks supervised by Adrian Weller, from the Machine Learning Group, and Matthew Wicker.

I have also spent a summer with Anima Anandkumar and Rafal Kocielnik at the AI + Science Lab, at Caltech. Here, I worked on applied ML problems - under the theme of automatic bias discovery in LLMs and text-to-image models.

In my free time, I love playing cricket. I also enjoy the outdoors, particularly exploring national parks and mountains, and travel.

Interests

  • Robust Generative Modelling
  • Data Acquisition
  • AI for Science

Academia

University of Oxford
2024 - present
Ph.D. Statistics and Machine Learning
University of Cambridge
2020 - 2024
B.A, M.Eng. Information and Computer Engineering

Selected Works

Locking Machine Learning Models into Hardware, 2024, Preprint
Eleanor Clifford*, Adhithya Saravanan*, Harry Langford*, Cheng Zhang, Yiren Zhao, Robert Mullins, Ilia Shumailov, Jamie Hayes
Certification of Individual Fairness in Bayesian Neural Networks, 2024, M.Eng. Dissertation
Adhithya Saravanan
Exploring social bias in downstream applications of text-to-image foundation models, 2023, I Can't Believe It's Not Better, NeurIPS
Adhithya Saravanan*, Rafal Kocielnik*, Roy Jiang, Pengrui Han, Anima Anandkumar