From the 1 of 19 linked papers with an AI index.
6 papers · 1 filter
An analysis of binary isotonic regression: degrees of freedom and implications for calibration
Raphael Rossellini, Rina Foygel Barber, Zhimei Ren +1
The paper provides a sharp finite‑sample bound on the worst‑case degrees of freedom of binary isotonic regression and uses this result to derive a distribution‑free guarantee on th…
Distribution-free two-sample testing with blurred total variation distance
Rohan Hore, Rina Foygel Barber
Two-sample testing, where we aim to determine whether two distributions are equal or not equal based on samples from each one, is challenging if we cannot place assumptions on the…
Assumption-free stability for ranking problems
Ruiting Liang, Jake A. Soloff, Rina Foygel Barber +1
In this work, we consider ranking problems among a finite set of candidates: for instance, selecting the top- items among a larger list of candidates or obtaining the full ranki…
Building a stable classifier with the inflated argmax
Jake A. Soloff, Rina Foygel Barber, Rebecca Willett
We propose a new framework for algorithmic stability in the context of multiclass classification. In practice, classification algorithms often operate by first assigning a continuo…
Is Algorithmic Stability Testable? A Unified Framework under Computational Constraints
Yuetian Luo, Rina Foygel Barber
Algorithmic stability is a central notion in learning theory that quantifies the sensitivity of an algorithm to small changes in the training data. If a learning algorithm satisfie…
Online conformal prediction with decaying step sizes
Anastasios N. Angelopoulos, Rina Foygel Barber, Stephen Bates
We introduce a method for online conformal prediction with decaying step sizes. Like previous methods, ours possesses a retrospective guarantee of coverage for arbitrary sequences.…