7 papers
Testing For Distribution Shifts with Conditional Conformal Test Martingales
Shalev Shaer, Yarin Bar, Drew Prinster +1
We propose a sequential test for detecting arbitrary distribution shifts that allows conformal test martingales (CTMs) to work under a fixed, reference-conditional setting. Existin…
Prediction-Powered Semi-Supervised Learning with Online Power Tuning
Noa Shoham, Ron Dorfman, Shalev Shaer +2
Prediction-Powered Inference (PPI) is a recently proposed statistical inference technique for parameter estimation that leverages pseudo-labels on both labeled and unlabeled data t…
Summary of the NOTSOFAR-1 Challenge: Highlights and Learnings
Igor Abramovski, Alon Vinnikov, Shalev Shaer +4
The first Natural Office Talkers in Settings of Far-field Audio Recordings (NOTSOFAR-1) Challenge is a pivotal initiative that sets new benchmarks by offering datasets more represe…
Protected Test-Time Adaptation via Online Entropy Matching: A Betting Approach
Yarin Bar, Shalev Shaer, Yaniv Romano
We present a novel approach for test-time adaptation via online self-training, consisting of two components. First, we introduce a statistical framework that detects distribution s…
NOTSOFAR-1 Challenge: New Datasets, Baseline, and Tasks for Distant Meeting Transcription
Alon Vinnikov, Amir Ivry, Aviv Hurvitz +16
We introduce the first Natural Office Talkers in Settings of Far-field Audio Recordings (``NOTSOFAR-1'') Challenge alongside datasets and baseline system. The challenge focuses on…
Model-X Sequential Testing for Conditional Independence via Testing by Betting
Shalev Shaer, Gal Maman, Yaniv Romano
This paper develops a model-free sequential test for conditional independence. The proposed test allows researchers to analyze an incoming i.i.d. data stream with any arbitrary dep…
Learning to Increase the Power of Conditional Randomization Tests
Shalev Shaer, Yaniv Romano
The model-X conditional randomization test is a generic framework for conditional independence testing, unlocking new possibilities to discover features that are conditionally asso…