Explore >> Select a destination
|
You are here 
|
www.ethanepperly.com | ||
| | | | |
www.someweekendreading.blog
|
|
| | | | | [Warning: Post contains full frontal nerdity. Bug reports appreciated!] I finally got a copy of Pham-Gia's paper on the distribution of the ratio of 2 independent Beta-distributed random variables. While I still have some childhood trauma around hypergeometric functions like ${}_{2}F_{1}()$ and its even scarier big brother ${}_{3}F_{2}()$... it's time to face my fears. | |
| | | | |
infiniteopt.github.io
|
|
| | | | | ||
| | | | |
lucatrevisan.wordpress.com
|
|
| | | | | Today we will see how to use the analysis of the multiplicative weights algorithm in order to construct pseudorandom sets. The method will yield constructions that are optimal in terms of the size of the pseudorandom set, but not very efficient, although there is at least one case (getting an ``almost pairwise independent'' pseudorandom generator)... | |
| | | | |
iclr-blogposts.github.io
|
|
| | | Diffusion Models, a new generative model family, have taken the world by storm after the seminal paper by Ho et al. [2020]. While diffusion models are often described as a probabilistic Markov Chains, their underlying principle is based on the decade-old theory of Stochastic Differential Equations (SDE), as found out later by Song et al. [2021]. In this article, we will go back and revisit the 'fundamental ingredients' behind the SDE formulation and show how the idea can be 'shaped' to get to the modern form of Score-based Diffusion Models. We'll start from the very definition of the 'score', how it was used in the context of generative modeling, how we achieve the necessary theoretical guarantees and how the critical design choices were made to finally arri... | ||
