Visiting Aaditya Ramdas @ CMU
Invited by Prof. Ramdas to work on extensions of Conformal Prediction.
PhD Candidate in Trustworthy AI
Developing certified AI systems for safety-critical transportation applications at SNCF and Institut de Mathématiques de Toulouse through the DEEL project. Interested in distribution-free uncertainty quantification with guarantees, such as conformal prediction. Also interested in robustness, explainability, and related fields.
"Une intelligence qui, pour un instant donné, connaîtrait toutes les forces dont la nature est animée, et la situation respective des êtres qui la composent, si d'ailleurs elle était assez vaste pour soumettre ces données à l'analyse, embrasserait dans la même formule les mouvements des plus grands corps de l'univers et ceux du plus léger atome : rien ne serait incertain pour elle, et l'avenir comme le passé, serait présent à ses yeux." - M. Le Marquis de Laplace
Invited by Prof. Ramdas to work on extensions of Conformal Prediction.
I was granted three scholarships for a future research stay abroad.
Our new work significantly improves an existing approach to robust CP, and proposes the first guarantee in a second setting. Available on HAL: https://hal.science/hal-04936823/
TBD
Robust Conformal Prediction using Lipschitz-by-Design Neural Networks
Developing trustworthy object detection systems for railway signaling using conformal prediction and risk control
Learning domain invariant representations through joint Wasserstein distance minimization