If you are at @icml2022, come to our spotlight talk: Thursday, 10:30-12:00 (Talk: 11:00-11:05), Session 8, Track 10, Room 310. Presentation: icml.cc/Conferences/20… Paper: arxiv.org/abs/2102.13640 Joint work with: Jakob Weissteiner, Hanna Wutte, Jakob Heiss, and Josef Teichmann

If you are interested in preference learning in combinatorial domains, you might like our two new #IJCAI2022 papers: 👇

1. "Monotone-Value Neural Networks: Exploiting Preference Monotonicity in Combinatorial Assignment": arxiv.org/abs/2109.15117 2. "Fourier Analysis-based Iterative Combinatorial Auctions": arxiv.org/abs/2009.10749

If you are at #IJCAI2022, you can see both talks, today, in the Multi-Agent-Systems session, from 3:30pm-3:42pm. Joint work with: Jakob Weissteiner, Jakob Heiss, Chris Wendler, Ben Lubin, Julien Siems, and Markus Püschel. Universität Zürich ETH Zurich ETH AI Center European Research Council (ERC)

#Opera 11.00 ist da und extrem gut! Stapelbare Tabs, endlich Erweiterungen und weitere neue Funktionen! Da fällt mir die Browserwahl schwer.

Jakob Heiss will present his ICML paper "NOMU - Neural Optimization-based Model Uncertainty" at the Uncertainty in AI reading group today at 5:30pm (Berlin time). uncertainty-reading-group.github.io/2021-11-28-tal… Co-author: Jakob Weissteiner, Hanna Wutte, Sven Seuken, Josef Teichmann

neue Version vom Profizocker Kampfsimulator: profizocker.aktiv-forum.com/h14-siedler-ka…

This week at BIRS: Uncertainty Quantification in Neural Network Models birs.ca/events/2025/5-…

ICLR 2026! 🎉 Our paper "CLEAR: Calibrated Learning for Epistemic and Aleatoric Risk", accepted ICLR 2026. Where does prediction uncertainty come from? Aleatoric (measurement noise) or epistemic (limited data)? Most methods only address one. CLEAR addresses both. (1/4)

CLEAR wraps around any base model with just two calibration parameters, no retraining. It determines how much each uncertainty source contributes. Compatible with any pair of estimators (ensembles + quantile regression), using ideas from conformal prediction. (2/4)

On 17 real-world datasets with ensembles + quantile regression: - 28.3% tighter intervals vs aleatoric-only baselines - 17.5% tighter vs epistemic-only baselines - Top method on 15 of 17 datasets Similar gains with Deep Ensembles & Quantile NNs confirm generalizability. (3/4)

CLEAR is available as an open-source Python package, so feel free to try it: 🐍 pip install clear-uq 💻 unco3892.github.io/clear/ 📄 openreview.net/forum?id=RY4IH… 🔗 github.com/Unco3892/clear Joint work with my great co-authors juro bodik , Jakob Heiss, and Bin Yu. (4/4)

Hab schon über 1200 Visits/Tag auf meinem DSO-Kampfsimulator: http://is.gd/0hcvZ4