/explore

Click through on any links that interest you or select the planets on the right to continue exploring the Outer Web.
You are here

 seanzhang.me
EM in a nutshell - Ramblings on Deep Learning
| | kyunghyuncho.me
Amortized Mixture of Gaussians (AMoG): A Proof of Concept for "Learning to X", or how I re-discovered simulation-based inference - Kyunghyun Cho
3.7 parsecs away

Travel
| |
| | francisbach.com
Scaling laws of optimization - Machine Learning Research Blog
3.6 parsecs away

Travel
| | [AI summary] This text discusses the scaling laws of optimization in machine learning, focusing on asymptotic expansions for both strongly convex and non-strongly convex cases. It covers the derivation of performance bounds using techniques like Laplace's method and the behavior of random minimizers. The text also explains the 'weird' behavior observed in certain plots, where non-strongly convex bounds become tight under specific conditions. The analysis connects theoretical results to practical considerations in optimization algorithms.
| | fa.bianp.net
On the Convergence of the Unadjusted Langevin Algorithm
3.3 parsecs away

Travel
| | The Langevin algorithm is a simple and powerful method to sample from a probability distribution. It's a key ingredient of some machine learning methods such as diffusion models and differentially private learning. In this post, I'll derive a simple convergence analysis of this method in the special case when the ...
| | theorydish.blog
FORC 2024 - CFP - Theory Dish
12.0 parsecs away

Travel
| The 5th annual Symposium on Foundations of Responsible Computing (FORC) will be held on June 12-14, 2024, at Harvard University in Cambridge, MA. Call for papers is out. Please send your strong papers for another success successful instalment of FORC. FORC is a forum for mathematical research in computation and society writ large. The Symposium...