Samuel Vaiter

samuelvaiter.com

20 February 2025 15:05

📣 New preprint 📣 Learning Theory for Kernel Bilevel Optimization w/ @fareselkhoury.bsky.social E. Pauwels @michael-arbel.bsky.social We provide generalization error bounds for bilevel optimization problems where the inner objective is minimized over a RKHS. arxiv.org/abs/2502.08457

Samuel Vaiter

samuelvaiter.com

14 February 2025 19:45

📢 New preprint 📢 Bilevel gradient methods and Morse parametric qualification w/ J. Bolte, T. Lê, E. Pauwels We study bilevel optimization with a nonconvex inner objective. To do so, we propose a new setting (Morse parametric qualification) to study bilevel algorithms. arxiv.org/abs/2502.09074

Preetum Nakkiran

preetumnakkiran.bsky.social

11 February 2025 21:02

Paper🧵 (cross-posted at X): When does composition of diffusion models "work"? Intuitively, the reason dog+hat works and dog+horse doesn’t has something to do with independence between the concepts being composed. The tricky part is to formalize exactly what this means. 1/

Fabian Schaipp

fschaipp.bsky.social

05 February 2025 10:14

Learning rate schedules seem mysterious? Why is the loss going down so fast during cooldown? Turns out that this behaviour can be described with a bound from *convex, nonsmooth* optimization. A short thread on our latest paper 🚞 arxiv.org/abs/2501.18965

Mathieu Blondel

mblondel.bsky.social

31 January 2025 22:59

Really proud of these two companion papers by our team at GDM: 1) Joint Learning of Energy-based Models and their Partition Function arxiv.org/abs/2501.18528 2) Loss Functions and Operators Generated by f-Divergences arxiv.org/abs/2501.18537 A thread.