5 papers
Learning Confidence Ellipsoids and Applications to Robust Subspace Recovery
Chao Gao, Liren Shan, Vaidehi Srinivas +1
We study the problem of finding confidence ellipsoids for an arbitrary distribution in high dimensions. Given samples from a distribution and a confidence parameter , the g…
Online Conformal Prediction with Efficiency Guarantees
Vaidehi Srinivas
We study the problem of conformal prediction in a novel online framework that directly optimizes efficiency. In our problem, we are given a target miscoverage rate , and a t…
New Tools for Smoothed Analysis: Least Singular Value Bounds for Random Matrices with Dependent Entries
Aditya Bhaskara, Eric Evert, Vaidehi Srinivas +1
We develop new techniques for proving lower bounds on the least singular value of random matrices with limited randomness. The matrices we consider have entries that are given by p…
Computing High-dimensional Confidence Sets for Arbitrary Distributions
Chao Gao, Liren Shan, Vaidehi Srinivas +1
We study the problem of learning a high-density region of an arbitrary distribution over . Given a target coverage parameter , and sample access to an arbitrary d…
Volume Optimality in Conformal Prediction with Structured Prediction Sets
Chao Gao, Liren Shan, Vaidehi Srinivas +1
Conformal Prediction is a widely studied technique to construct prediction sets of future observations. Most conformal prediction methods focus on achieving the necessary coverage…