no code implementations • 25 Oct 2023 • Saiteja Utpala, Alex Gu, Pin Yu Chen
Recently, code language models have achieved notable advancements in addressing a diverse array of essential code comprehension and generation tasks.
1 code implementation • 24 Oct 2023 • Saiteja Utpala, Sara Hooker, Pin Yu Chen
Numerous studies have highlighted the privacy risks associated with pretrained large language models.
1 code implementation • 10 Oct 2022 • Saiteja Utpala, Andi Han, Pratik Jawanpuria, Bamdev Mishra
We present Rieoptax, an open source Python library for Riemannian optimization in JAX.
no code implementations • 8 Aug 2022 • Saiteja Utpala, Praneeth Vepakomma, Nina Miolane
In that spirit, the only geometric statistical query for which a differential privacy mechanism has been developed, so far, is for the release of the sample Fr\'echet mean: the \emph{Riemannian Laplace mechanism} was recently proposed to privatize the Fr\'echet mean on complete Riemannian manifolds.
no code implementations • 13 Jul 2022 • Saiteja Utpala, Bharath K. Sriperumbudur
We propose estimators that shrink the $U$-statistic estimator of the Bochner integral towards a pre-specified target element in the Hilbert space.
no code implementations • 1 Jan 2021 • Saiteja Utpala, Piyush Rai
We provide a detailed formal analysis of the \emph{side-effects} of Isotonic Regression when used for regression calibration.
no code implementations • NeurIPS Workshop ICBINB 2020 • Saiteja Utpala, Piyush Rai
Deep learning models are often poorly calibrated, i. e., they may produce overconfident predictions that are wrong, implying that their uncertainty estimates are unreliable.
no code implementations • 28 Feb 2020 • Saiteja Utpala, Piyush Rai
It is therefore desirable to have models that produce predictive uncertainty estimates that are reliable.