news

Oct 10, 2024 Our paper on measuring bias in text-to-image models with a proportional representation metric has been accepted at the NeurIPS 2024 Workshop on Algorithmic Fairness through the lens of Metrics and Evaluation.
Sep 26, 2024 Our paper on uncertainty quantification for high-dimensional learning has been selected as a spotlight at the NeurIPS 2024.
Sep 26, 2024 Our paper on multi-group proportional representation has been accepted at the NeurIPS 2024.
Sep 26, 2024 Our paper about mechanistic interpretability was one of the 5 papers accepted as an oral contribution (top 3.6%) at the ICML Mechanistic Interpretability Workshop 2024 and also has been accepted at the NeurIPS 2024!
Jul 21, 2024 Our paper on implicit bias of gradient descent on overparametrization models is out on arXiv.
Jul 1, 2024 Our paper about confidence intervals for total variation-based image reconstruction MRI was accepted at the ECCV 2024.
Jun 21, 2024 Our paper about reweighted sampling strategies for improving uncertainty quantification in Fourier imaging was accepted at the Cosera 2024.
May 10, 2024 Our paper about tunning-free sparse regression with global linear convergence was accepted at the COLT 2024.
Apr 30, 2024 Our policy brief about AI, arbitrariness, and algorithmic leviathans got accepted at the 2024 G20 Summit.
Feb 1, 2024 I started as a research scholar at Harvard University.
Jun 22, 2023 Our rigorous uncertainty quantification for sparse MRI got the Best Student Paper Award at the ICASSP 2023.
Jan 24, 2023 I was one of the eight invited speakers chosen to represent the Technical University of Munich at the founding ceremony of the TUM School of Computation, Information and Technology.
May 9, 2022 Invited to give a talk on the Focus Program on Data Science, Approximation Theory, and Harmonic Analysis at the Fields Institute.
Dec 1, 2021 The first method for Basis Pursuit (and the LASSO) with a provable global linear rate under minimal assumptions is out. Spotlight (top 3%) at the NeurIPS 2021.
Jun 22, 2020 Our work on group testing for COVID has been highlighted by David Donoho at the SIAM Conference on Mathematics of Data Science.