Selecting informative conformal prediction sets with false coverage rate control
In our upcoming BDI Machine Learning seminar, we’re thrilled to welcome Dr Ruth Heller, Professor of Statistics from the Department of Statistics and Operations Research at Tel-Aviv University, Israel. We’re delighted to host Ruth in what promises to be a great talk!
Date: Friday 6 December
Time: 15:00 – 16:00
Talk title: Selecting informative conformal prediction sets with false coverage rate control
Location: BDI/OxPop Seminar room 1
Abstract:
In supervised learning, including regression and classification, conformal methods provide prediction sets for the outcome/label with finite sample coverage for any machine learning predictors. We consider here the case where such prediction sets come after a selection process. The selection process requires that the selected prediction sets be `informative’ in a well-defined sense. We consider both the classification and regression settings where the analyst may consider as informative only the sample with prediction sets small enough, excluding null values, or obeying other appropriate `monotone’ constraints. We develop a unified framework for building such informative conformal prediction sets while controlling the false coverage rate (FCR) on the selected sample. While conformal prediction sets after selection have been the focus of much recent literature in the field, the new introduced procedures, called InfoSP and InfoSCOP, are to our knowledge the first ones providing FCR control for informative prediction sets.
We show the usefulness of our resulting procedures on real and simulated data. This approach is applicable to neuroimaging, e.g., to provide prediction sets of medical (in particular neurological and psychiatric) diagnoses using the high dimensional individual functional MRI data.
Bio: Ruth Heller received her PhD in Statistics in 2007 from Tel-Aviv University with Felix Abramovich and Yoav Benjamini as her thesis advisors. Prior to returning to Tel-Aviv University, she spent the years 2007-2009 as the Mark O. Winkelman Distinguished Scholar in Residence Visiting Lecturer of Statistics at the University of Pennsylvania, and the years 2009-2011 as a Senior Lecturer in the Industrial engineering and management faculty at the Technion. Ruth is a Professor of Statistics and Operations Research at Tel-Aviv University. Her research focuses on multiple comparisons and selective inference, with applications to the medical and biological sciences. She develops methods for establishing replicability of scientific results while controlling for appropriate error rates. She also designs multiple testing procedures targeted towards optimizing well defined power objectives. She is interested in causal inference and conformal inference, where her research focuses on providing useful uncertainty guarantees to accompany causal discoveries or predictions.
Website: www.math.tau.ac.il/~ruheller
Date:
6 December 2024, 15:00
Venue:
Big Data Institute, Old Road Campus OX3 7LF
Venue Details:
Seminar room 1
Speaker:
Dr Ruth Heller (Tel Aviv University)
Organising department:
Big Data Institute (NDPH)
Organisers:
Prof Christopher Yau (University of Oxford),
Sumeeta Maheshwari (University of Oxford),
Professor Thomas Nichols (University of Oxford)
Organiser contact email address:
sumeeta.maheshwari@ndph.ox.ac.uk
Part of:
Machine Learning@BDI Seminar Series
Booking required?:
Not required
Audience:
Members of the University only
Editor:
Sumeeta Maheshwari
