no code implementations • 25 Mar 2024 • John C. Duchi, Suyash Gupta, Kuanhao Jiang, Pragya Sur
We address the challenge of constructing valid confidence intervals and sets in problems of prediction across multiple environments.
no code implementations • 14 Sep 2023 • Yufan Li, Pragya Sur
This approach struggles when (i) covariates are non-Gaussian with heavy tails or asymmetric distributions, (ii) rows of the design exhibit heterogeneity or dependencies, and (iii) reliable feature covariance estimates are lacking.
1 code implementation • 21 Oct 2022 • Lijia Zhou, Frederic Koehler, Pragya Sur, Danica J. Sutherland, Nathan Srebro
We prove a new generalization bound that shows for any class of linear predictors in Gaussian space, the Rademacher complexity of the class and the training error under any continuous loss $\ell$ can control the test error under all Moreau envelopes of the loss $\ell$.
1 code implementation • 11 Jul 2022 • Cathy Shyr, Pragya Sur, Giovanni Parmigiani, Prasad Patil
In the regression setting, we provide theoretical guidelines based on an analytical transition point to determine whether it is more beneficial to merge or to ensemble for boosting with linear learners.
no code implementations • 20 May 2022 • Kuanhao Jiang, Rajarshi Mukherjee, Subhabrata Sen, Pragya Sur
In recent times, inference for the ATE in the presence of high-dimensional covariates has been extensively studied.
no code implementations • 9 Apr 2022 • Tengyuan Liang, Subhabrata Sen, Pragya Sur
We provide a "path-wise" characterization of the overlap between the output of the Langevin algorithm and the planted signal.
no code implementations • 20 Jun 2020 • Zhun Deng, Frances Ding, Cynthia Dwork, Rachel Hong, Giovanni Parmigiani, Prasad Patil, Pragya Sur
We study an adversarial loss function for $k$ domains and precisely characterize its limiting behavior as $k$ grows, formalizing and proving the intuition, backed by experiments, that observing data from a larger number of domains helps.
no code implementations • 4 Apr 2020 • Cynthia Dwork, Christina Ilvento, Guy N. Rothblum, Pragya Sur
Our principal conceptual result is an extraction procedure that learns the underlying truth; moreover, the procedure can learn an approximation to this truth given access to a weak form of the oracle.
no code implementations • 5 Feb 2020 • Tengyuan Liang, Pragya Sur
This paper establishes a precise high-dimensional asymptotic theory for boosting on separable data, taking statistical and computational perspectives.
no code implementations • 25 Apr 2018 • Emmanuel J. Candes, Pragya Sur
This paper rigorously establishes that the existence of the maximum likelihood estimate (MLE) in high-dimensional logistic regression models with Gaussian covariates undergoes a sharp `phase transition'.
no code implementations • 5 Jun 2017 • Pragya Sur, Yuxin Chen, Emmanuel J. Candès
When used for the purpose of statistical inference, logistic models produce p-values for the regression coefficients by using an approximation to the distribution of the likelihood-ratio test.