/explore
|
You are here 
|
stevensoojin.kim | ||
| | | | |
almostsuremath.com
|
|
| | | | | The martingale property is strong enough to ensure that, under relatively weak conditions, we are guaranteed convergence of the processes as time goes to infinity. In a previous post, I used Doob's upcrossing inequality to show that, with probability one, discrete-time martingales will converge at infinity under the extra condition of $latex {L^1}&fg=000000$-boundedness. Here, I... | |
| | | | |
francisbach.com
|
|
| | | | | [AI summary] This mathematical post explores the geometry of positive semi-definite matrices using the von Neumann entropy and related Bregman divergences to derive concentration inequalities for random matrices. | |
| | | | |
djalil.chafai.net
|
|
| | | | | This post is devoted to a concentration inequality of Lipschitz functions for a class of projected probability distributions on the unit sphere of $\mathbb{R}^n$, $n\geq2$, \[ \mathbb{S}^{n-1}=\Bigl\{x\in\mathbb{R}^n:|x|:=\sqrt{x_1^2+\cdots+x_n^2}=1\Bigr\}. \] We take this opportunity to recall various aspects of concentration for Gaussians. Concentration. Let... | |
| | | | |
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)... | ||
