Posts by Collection

portfolio

Portfolio item number 1

Short description of portfolio item number 1

Portfolio item number 2

Short description of portfolio item number 2

publications

Structure-sensitive Testimonial Norms

Listening to scientific rockstars is not good for science.

Höltgen, B.: "Structure-sensitive testimonial norms." European Journal for Philosophy of Science 11:80. 2021.

Encoding Causal Macrovariables

An algorithm for causal representation learning and a reflection on causal variables. My first master thesis.

Höltgen, B.: "Encoding causal macrovariables." NeurIPS Workshop: Causal Inference & Machine Learning: Why now?. 2021.

DeDUCE: Generating Counterfactual Explanations Efficiently

An algorithm for generating counterfactual explanations. My second master thesis.

Höltgen, B., Schut, L., Brauner, J., Gal, Y.: "DeDUCE: Generating counterfactual explanations efficiently." NeurIPS Workshop: eXplainable AI approaches for debugging and diagnosis. 2021.

Moral Discourse Boosts Confidence in Moral Judgments

The title says it all.

Heinzelmann, N., Höltgen, B., and Tran, V.: "Moral discourse boosts confidence in moral judgments." Philosophical Psychology 34:8, 1192-1216. 2021.

Prioritized Training on Points that are Learnable, Worth Learning, and Not Yet Learned

An online batch selection algorithm for time-efficient training of large ML models.

Mindermann, S., Brauner, J., Razzak, M., Sharma, M., Kirsch, W., Xu, W., Höltgen, B., Gomez, A.N., Morisot, A., Farquhar, S., Gal, Y.: "Prioritized training on points that are learnable, worth learning, and not yet learned." ICML. 2022.

On the Richness of Calibration

Exploring the concept of calibration and different ways of measuring it.

Höltgen, B., Williamson, R.C.: "On the richness of calibration." ACM FAccT. 2023.

Practical Foundations for Probability: Prediction Methods and Calibration

How to understand probability.

Formalising Causal Inference as Prediction on a Target Population

Causal inference models that can be tested, for more insights and accountability.

Reconsidering Fairness Through Unawareness From the Perspective of Model Multiplicity

Using protected attributes can increase disparate impact without increasing accuracy.

Höltgen, B., Oliver, N.: "Reconsidering fairness through unawareness from the perspective of model multiplicity." ACM EAAMO. 2025.

A Thoughtful Narrative Emerges

A comment on Sabina Leonelli’s work on Environmental Intelligence.

Höltgen, B.: "A thoughtful narrative emerges." Harvard Data Science Review, 7:4. 2025.

Position: The Categorization of Race in ML is a Flawed Premise

ML research oversimplifies race and we need to learn how to move beyond categories.

Doh, M., Höltgen, B., Riccio, P., Oliver, N.: "Position: The categorization of race in ML is a flawed premise." ICML. 2025.

The Costs of Pretending That There Are Data-Generating Probability Distributions in the Social World

We should model ML without true distributions, at least in social settings.

Höltgen, B., Williamson, R.C.: "The costs of pretending that there are data-generating probability distributions in the social world." ACM FAccT. 2026.

teaching

Teaching experience 1

Undergraduate course, University 1, Department, 2014

This is a description of a teaching experience. You can use markdown like any other post.

Teaching experience 2

Workshop, University 1, Department, 2015