Zobrazeno 1 - 10
of 290
pro vyhledávání: '"Tibshirani, Ryan J."'
Common practice in modern machine learning involves fitting a large number of parameters relative to the number of observations. These overparameterized models can exhibit surprising generalization behavior, e.g., ``double descent'' in the prediction
Externí odkaz:
http://arxiv.org/abs/2410.01259
We consider a novel multivariate nonparametric two-sample testing problem where, under the alternative, distributions $P$ and $Q$ are separated in an integral probability metric over functions of bounded total variation (TV IPM). We propose a new tes
Externí odkaz:
http://arxiv.org/abs/2409.15628
We study approximations to the Moreau envelope -- and infimal convolutions more broadly -- based on Laplace's method, a classical tool in analysis which ties certain integrals to suprema of their integrands. We believe the connection between Laplace'
Externí odkaz:
http://arxiv.org/abs/2406.02003
We study the behavior of optimal ridge regularization and optimal ridge risk for out-of-distribution prediction, where the test distribution deviates arbitrarily from the train distribution. We establish general conditions that determine the sign of
Externí odkaz:
http://arxiv.org/abs/2404.01233
We analyze the statistical properties of generalized cross-validation (GCV) and leave-one-out cross-validation (LOOCV) applied to early-stopped gradient descent (GD) in high-dimensional least squares regression. We prove that GCV is generically incon
Externí odkaz:
http://arxiv.org/abs/2402.16793
Maximum mean discrepancy (MMD) refers to a general class of nonparametric two-sample tests that are based on maximizing the mean difference over samples from one distribution $P$ versus another $Q$, over all choices of data transformations $f$ living
Externí odkaz:
http://arxiv.org/abs/2309.02422
We study the problem of uncertainty quantification for time series prediction, with the goal of providing easy-to-use algorithms with formal guarantees. The algorithms we present build upon ideas from conformal prediction and control theory, are able
Externí odkaz:
http://arxiv.org/abs/2307.16895
Autor:
Ding, Tiffany, Angelopoulos, Anastasios N., Bates, Stephen, Jordan, Michael I., Tibshirani, Ryan J.
Standard conformal prediction methods provide a marginal coverage guarantee, which means that for a random test point, the conformal prediction set contains the true label with a user-specified probability. In many classification problems, we would l
Externí odkaz:
http://arxiv.org/abs/2306.09335
De Finetti's theorem, also called the de Finetti-Hewitt-Savage theorem, is a foundational result in probability and statistics. Roughly, it says that an infinite sequence of exchangeable random variables can always be written as a mixture of independ
Externí odkaz:
http://arxiv.org/abs/2304.03927