ArXiv TLDR

Umut Şimşekli

2 papers · Latest:

Machine Learning

Variational Inference for Lévy Process-Driven SDEs via Neural Tilting

This paper introduces a neural exponential tilting framework for variational inference in Lévy-driven SDEs, addressing challenges in modeling extreme events.

2605.10934
Machine Learning

Generalization at the Edge of Stability

This paper introduces 'sharpness dimension' and a new generalization bound to explain why neural networks generalize well when trained at the edge of stability.

2604.19740

📬 Weekly AI Paper Digest

Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.