this paper is a pretty impressive tour de force in neural network training: arxiv.org/abs/2410.11081 pretty inspiring to me -- network isn't converging? rigorously monitor every term in your loss to identify where in the architecture something is going wrong!

Oscillations naturally emerge in large crowds. That's because your brain works by oscillating. Emergence of collective oscillations in massive human crowds www.nature.com/articles/s41... #neuroscience

what's the status on using jax for image experiments (e.g. with diffusion models)? it seems like standard packages like huggingface diffusers have much less robust implementations of the same neural networks than the pytorch counterpart?

📣 Excited to receive the 💥 NSF CAREER 💥 Award. Our group is looking for PhD students and postdocs interested in the Nonlinear Dynamics and the Physics of Living Systems, with support from NSF, HFSP, and other sources. We’d appreciate your help in spreading the word! @ucsdphysci.bsky.social

some really nice new work by @jiequnh.bsky.social and collaborators arxiv.org/abs/2409.08526 of course i'm super biased, but i think that figuring out how to solve high-dimensional scientific computing problems with ML has potentially very high impact. i'd love to see more work like this

what are the most important open problems in molecular simulation right now that stand to benefit from ML-based methods? any good reviews or references to get up to speed rapidly? @gcorso.bsky.social @hannes-stark.bsky.social?

there's a lot of interest right now in using diffusion and flow matching models for sampling (i.e., no data but access to the energy). is anyone aware of works using diffusion models or score-based approaches for data assimilation? seems like it could be a natural evolution of kalman filter ideas.

question for the academics: how do you manage your (ever-growing) reading list? do you have a few dedicated reading blocks per week, where you tackle some papers you've been interested in? do you only read as you need to solve a research problem? how do you fit textbooks into this?

quite excited to read this in the new year: arxiv.org/abs/2410.10523