/explore
|
You are here 
|
lucatrevisan.wordpress.com | ||
| | | | |
jeremykun.com
|
|
| | | | | Hard to believe Sanjeev Arora and his coauthors consider it"a basic tool [that should be] taught to all algorithms students together with divide-and-conquer, dynamic programming, and random sampling."Christos Papadimitriou calls it"so hard to believe that it has been discovered five times and forgotten." It has formed the basis of algorithms inmachine learning, optimization, game theory, | |
| | | | |
francisbach.com
|
|
| | | | | [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. | |
| | | | |
windowsontheory.org
|
|
| | | | | Previous post: ML theory with bad drawings Next post: What do neural networks learn and when do they learn it, see also all seminar posts and course webpage. Lecture video (starts in slide 2 since I hit record button 30 seconds too late - sorry!) - slides (pdf) - slides (Powerpoint with ink and animation)... | |
| | | | |
dominiczypen.wordpress.com
|
|
| | | For $latex A, B \subseteq \omega$ we write $latex A \subseteq^* B$ if $latex A\setminus B$ is finite, and we write $latex A\simeq^* B$ if $latex A\subseteq^* B$ and $latex B\subseteq^* A$. A tower is a collection $latex {\cal T}$ of co-infinite subsets of $latex \omega$ such that for all $latex A\neq B\in {\cal T}$... | ||
