iiinova — where your digital self keeps evolving

Tobias Sutter

@tobiassutter.bsky.social

51 followers 61 following 3 posts

Associate Professor, University of St.Gallen

Posts Replies Media

Reposted by Tobias Sutter

Peter Selb @pselb.bsky.social · 15/12/2025

We @uni-konstanz.de are hiring a full professor in machine learning for our MSc program in Social and Economic Data Science: stellen.uni-konstanz.de/jobposting/6...

stellen.uni-konstanz.de

Full Professorship (W3) in Machine Learning

Deadline: January 31, 2026

01918

Tobias Sutter @tobiassutter.bsky.social · 22/07/2025

New print on optimal decision making by exploiting statistical concentration properties of the underlying data generating process … arxiv.org/pdf/2507.15215

000

Reposted by Tobias Sutter

David Boetius @davidboe.bsky.social · 17/07/2025

I‘ll be presenting my poster on solving probabilistic verification problems of NNs at ICML today! Meet me at poster E-2302 :)

Poster „Solving Probabilistic Verification Problems of Neural Networks using Branch and Bound“

041

Tobias Sutter @tobiassutter.bsky.social · 02/05/2025

To be presented at ICML 2025 arxiv.org/pdf/2405.17556

021

Tobias Sutter @tobiassutter.bsky.social · 18/03/2025

New preprint on optimal offline RL arxiv.org/pdf/2503.12283

arxiv.org

020

Reposted by Tobias Sutter

Felix Petersen @petersen.ai · 28/11/2024

I'm excited to share our NeurIPS 2024 paper "Newton Losses: Using Curvature Information for Learning with Differentiable Algorithms" 🤖. Paper link 📜: arxiv.org/abs/2410.19055

arxiv.org

Newton Losses: Using Curvature Information for Learning with Differentiable Algorithms

When training neural networks with custom objectives, such as ranking losses and shortest-path losses, a common problem is that they are, per se, non-differentiable. A popular approach is to continuou...

1184