publications
Publications by categories in reversed chronological order
2025
-
-
Train for the worst, plan for the best: Understanding token ordering in masked diffusionsInternational Conference of Machine Learning (Outstanding Paper Award), 2025 -
LoRA Training Provably Converges to a Low-Rank Global Minimum or It Fails Loudly (But it Probably Won’t Fail)International Conference of Machine Learning (Oral), 2025 -
2024
-
- Optimal acceleration for minimax and fixed-point problems is not uniqueInternational Conference on Machine Learning (Spotlight), 2024
2023
-
-
Time-Reversed Dissipation Induces Duality Between Minimizing Gradient Norm and Function ValueNeural Information Processing Systems, 2023