Differentiable Calibration Losses for Multi-Class Machine Learning Models

Modern classification models, especially deep neural networks, often output probability scores. These scores are commonly interpreted as confidence levels. For example, if a model assigns a probability of 70% to a class, one would expect the prediction to be correct approximately 70% of the time. A model satisfying this property is said to be well calibrated.

In practice, high predictive accuracy does not guarantee good calibration. Many modern classifiers are accurate but overconfident or underconfident. This is problematic when probability scores are used to support decisions, risk assessment, medical prediction, fraud detection, ranking systems, or any setting where the reliability of the predicted probabilities matters.

The objective of this PhD project is to develop differentiable calibration losses for multi-class machine learning models. The goal is to move beyond post-hoc calibration methods and design calibration criteria that can be directly incorporated into the training of neural networks.

We are seeking a motivated PhD candidate to work on a doctoral project at the intersection of machine learning, statistics, and reliable artificial intelligence., Master Degree or equivalent, Master Degree or equivalent

Research Field Computer science » Other

Education Level Master Degree or equivalent, * Master's degree in computer science, mathematics, statistics, data science or similar.

• Solid knowledge of machine learning techniques.
• Good Python programming skills.
• Fluency in English; knowledge of French is an asset but not mandatory.

Languages FRENCH

We offer:

The selected candidate will join ISBA/LIDAM at UCLouvain in a research environment combining statistics, machine learning, data analysis, and applied modeling.

• A full-time doctoral fellowship initially funded for 15 months through the UCLouvain FSR Projects scheme;
• A project with both methodological and empirical components;
• A stimulating and collaborative research environment within the renowned Institute of Statistics, Biostatistics and Actuarial Sciences (ISBA);
• The opportunity for personal growth through, for instance, participation in international conferences, doctoral courses, and collaboration with researchers in statistics, machine learning, and trustworthy AI.

Selection process