/explore
|
You are here 
|
tcsmath.github.io | ||
| | | | |
fa.bianp.net
Most proofs in optimization consist in using inequalities for a particular function class in some creative way. This is a cheatsheet with inequalities that I use most often. It considers class of functions that are convex, strongly convex and $L$-smooth. MathJax.Hub.Config({ extensions: ["tex2jax.js"], jax: ["input/TeX ... |
|
| | | | | ||
| | | | |
statisticaloddsandends.wordpress.com
Let's say we have a convex, differentiable function $latex f: \mathbb{R}^p \rightarrow \mathbb{R}$ and that we want to minimize it. In this previous post, we saw that a gradient descent step at time $latex t$ (from point $latex \beta^t$) could be viewed as the minimizer of a quadratic approximation of $latex f$ at $latex \beta^t$:... |
|
| | | | | ||
| | | | |
lucatrevisan.wordpress.com
(This is the sixth in a series of posts on online optimization techniques and their ``applications'' to complexity theory, combinatorics and pseudorandomness. The plan for this series of posts is to alternate one post explaining a result from the theory of online convex optimization and one post explaining an ``application.'' The first two posts were... |
|
| | | | | ||
| | | | |
nulliq.dev
In search of a better dot product |
|
| | | |||
