Search Results for author: Nicolas Deutschmann

Found 5 papers, 1 papers with code

Conformal Autoregressive Generation: Beam Search with Coverage Guarantees

no code implementations7 Sep 2023 Nicolas Deutschmann, Marvin Alberts, María Rodríguez Martínez

We introduce two new extensions to the beam search algorithm based on conformal predictions (CP) to produce sets of sequences with theoretical coverage guarantees.

Adaptive Conformal Regression with Jackknife+ Rescaled Scores

no code implementations31 May 2023 Nicolas Deutschmann, Mattia Rigotti, Maria Rodriguez Martinez

We address this with a new adaptive method based on rescaling conformal scores with an estimate of local score distribution, inspired by the Jackknife+ method, which enables the use of calibration data in conformal scores without breaking calibration-test exchangeability.

Conformal Prediction Prediction Intervals +1

Attention-based Interpretable Regression of Gene Expression in Histology

1 code implementation29 Aug 2022 Mara Graziani, Niccolò Marini, Nicolas Deutschmann, Nikita Janakarajan, Henning Müller, María Rodríguez Martínez

Interpretability of deep learning is widely used to evaluate the reliability of medical imaging models and reduce the risks of inaccurate patient recommendations.


Is Attention Interpretation? A Quantitative Assessment On Sets

no code implementations26 Jul 2022 Jonathan Haab, Nicolas Deutschmann, Maria Rodríguez Martínez

The debate around the interpretability of attention mechanisms is centered on whether attention scores can be used as a proxy for the relative amounts of signal carried by sub-components of data.

Binary Classification Multiple Instance Learning

Accelerating HEP simulations with Neural Importance Sampling

no code implementations29 Sep 2021 Nicolas Deutschmann, Niklas Götz

Virtually all high-energy-physics (HEP) simulations for the LHC rely on Monte Carlo using importance sampling by means of the VEGAS algorithm.

Cannot find the paper you are looking for? You can Submit a new open access paper.