Omead Pooladzandi ✈️ NeurIPS'24
@hessianfree.bsky.social
Optimization Generative Modeling @Caltech, PhD @UCLA. ex Research Scientist Intern @AIatMeta (opinions are my own) why is jax so difficult
Newton-Schulz isn't the answer even for instantaneous whitening. PSGD: MSE( Q.T Q H , I ) = 5.2e-3 Zero-Power NS 100 iterations: MSE( NS(G) , I ) = 8.2e-1 True Inverse: MSE( H^(-1/2) H H^(-1/2), I ) = 6.1e-3 PSGD whitens information significantly better than the Newton-Schulz iters found in Muon
Xilin is back at it again. Results are clear: damping hurts precision, but lower precision needs it if the underlying Hessian is extremely poorly conditioned.
PSGD tracking Muon on modded nanoGPT
Lol AI stats reviews consisted of one 5 rating: Top 10% of accepted papers with a confidence or 5 - absolutely certain. The reviewer raved and ranted about how good PSGD. And two confident 4 rejects with a score of 1. And one borderline reject with a confidence of 4.
SmolVLM was just released 🚀 It's a great, small, and fully open VLM that I'm really excited about for fine-tuning and on-device use cases 💻 It also comes with 0-day MLX support via mlx-vlm, here's it running at > 80 tok/s on my M1 Max 🤯
Just put together a starter pack for Deep Learning Theory. Let me know if you'd like to be included or suggest someone to add to the list! go.bsky.app/2qnppia
PSGD ❤️ MARS MARS is a new exciting variance reduction technique from @quanquangu.bsky.social 's group which can help stabilize and accelerate your deep learning pipeline. All that is needed is a gradient buffer. Here MARS speeds up the convergence of PSGD ultimately leading to a better solution.
Oftentimes PSGD will be slow to close plasticity resulting in slightly slower convergence but ultimately a better solution.
Okayyy I should actually start posting about PSGD here
Radon Transform (RT) was formulated in 1917 but remained useless in practice until CT scanners were invented in the 60s But RT isn't just for CTs. It's a sort of generalization of marginals in probability RT g(p,θ): Shoot rays at θ+90 & offset p, measure line integrals of f(x,y) along the ray 1/n
Starter packs are helpful as well as the twitter import tool chromewebstore.google.com/detail/sky-f...
Sky Follower Bridge - Chrome Web Store
Instantly find and follow the same users from your Twitter follows on Bluesky.
chromewebstore.google.com
Here, have PSGD-Kron and SOAP with FSDP2 support. Please go wild with it, let's see something finally replace ADAM. github.com/ethansmith20...
probably the best in-depth explanation i've seen on FSDP at the most granular levels, props to the authors dev-discuss.pytorch.org/t/fsdp-cudac...