Tobias Sutter

New print on optimal decision making by exploiting statistical concentration properties of the underlying data generating process …

arxiv.org/pdf/2507.15215

22.07.2025 04:35 — 👍 0    🔁 0    💬 0    📌 0

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

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

17.07.2025 17:01 — 👍 3    🔁 1    💬 0    📌 0

To be presented at ICML 2025

arxiv.org/pdf/2405.17556

02.05.2025 16:57 — 👍 2    🔁 1    💬 0    📌 0

New preprint on optimal offline RL

arxiv.org/pdf/2503.12283

18.03.2025 08:39 — 👍 2    🔁 0    💬 0    📌 0

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...

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

28.11.2024 01:49 — 👍 18    🔁 4    💬 1    📌 2