Tobias Sutter
@tobiassutter.bsky.social
📤 49
📥 60
📝 3
Associate Professor, University of St.Gallen
reposted by
Tobias Sutter
Peter Selb
18 days ago
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...
loading . . .
Full Professorship (W3) in Machine Learning
Deadline: January 31, 2026
https://stellen.uni-konstanz.de/jobposting/6fb92b2d8de7379a32133932a66b0d6b68b911920
0
15
19
New print on optimal decision making by exploiting statistical concentration properties of the underlying data generating process …
arxiv.org/pdf/2507.15215
5 months ago
0
0
0
reposted by
Tobias Sutter
David Boetius
6 months ago
I‘ll be presenting my poster on solving probabilistic verification problems of NNs at ICML today! Meet me at poster E-2302 :)
0
4
1
To be presented at ICML 2025
arxiv.org/pdf/2405.17556
8 months ago
0
2
1
New preprint on optimal offline RL
arxiv.org/pdf/2503.12283
loading . . .
https://arxiv.org/pdf/2503.12283
10 months ago
0
2
0
reposted by
Tobias Sutter
Felix Petersen
about 1 year ago
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
loading . . .
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...
https://arxiv.org/abs/2410.19055
1
18
6
you reached the end!!
feeds!
log in
