/explore
|
You are here 
|
cgad.ski | ||
| | | | |
fa.bianp.net
|
|
| | | | | 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 ... | |
| | | | |
blog.alexalemi.com
|
|
| | | | | ||
| | | | |
jaketae.github.io
|
|
| | | | | The other day, my friend and I were talking about our mutual friend Jeremy. "He's an oddball," my friend Sean remarked, to which I agreed. Out of nowhere, Jeremy had just told us that he would not be coming back to Korea for the next three years. "He is just about the most random person I know." And both of us, being aspiring statistics majors, began wondering: is there a systematic way of measuring randomness? It is from here that we went down the rabbit hole of Google and Wikipedia search. I ended up landing on entropy land, which is going to be the topic for today's post. It's a random post on the topic of randomness. | |
| | | | |
www.danieldjohnson.com
|
|
| | | I argue that hallucinations are a natural consequence of the language modeling objective, which focuses on simulating confident behavior even when that behavior is hard to predict, rather than predictable behaviors that take uncertainty into account. I also discuss five strategies for avoiding this mismatch. | ||
