[Survey Taken Thread]

By ancient tradition, if you take the survey you may comment saying you have done so here, and people will upvote you and you will get karma.

Let's make these comments a reply to this post. That way we continue the tradition, but keep the discussion a bit cleaner.

June 2014 or 2015?

After discussing diffusion of interesting news at the most recent London meetup, I was planning on asking something like this myself.

Futility Closet is nothing but "interesting stuff". It describes itself as "a collection of entertaining curiosities in history, literature, language, art, philosophy, and mathematics, designed to help you waste time as enjoyably as possible". It has more chess than I personally care for, but is updated with what I find to be novel content three times a day.

Conscious Entities is a blog on Philosophy of Mind. It takes an open position on a lot of questions we would consider to be settled on LessWrong, but I think it has value in a steel-manning / why-do-people-believe-this capacity.

(The categories on my feed reader are "Blogs", "CS", "Dance", "Econ", "Esoterica", "Maths/Stats", "Philosophy", "Science" and "Webcomics". I'd be interested in finding out how other people classify theirs.)

Here's a sampling of the best in my RSS reader:

• Scott Aaronson, theoretical computer science/physics
• Tyler Cowen, economics, Cowen is good about sharing surprising info
• Lambda the Ultimate, programming language theory
• John Baez, "from math to physics to earth science and biology, computer science and the technologies of today and tomorrow," plus stuff on catastrophic risk w.r.t. climate change.
• Jeremy Kun, computer science mostly
• The n-Category Cafe, "A group blog on math, physics and philosophy"
• Andrew Gelman, pointing out bad statistics in social science. More than once, I've revised my beliefs about some study months later when he points out a failure to replicate or other problem.
• Timothy Gowers, math, analysis I stuff recently, mostly over my head
• Terry Tao, math, number theory, mostly over my head
• matthen, math visualizations
• Gödel’s Lost Letter, theoretical computer science, complexity theory, often funny
• MIRI blog, interviews, research recaps, computer sciencey
• Overcoming Bias, X isn't about Y
• Dart Throwing Chimp, global politics
• Carl Shulman, effective altruism, thoughtful analysis
• Saturday Morning Breakfast Cereal, webcomic
• So Your Life is Meaningless, webcomic
• XKCD, webcomic
• hbd* chick, population genetics, star wars, emoticons
• Unqualified Reservations, neoreactionary, questioning everything since the enlightenment
• Yvain, psychology, rationality, relationships
• Ben Kuhn, effective altruism
• Katja Grace, rationality
• Brienne Strohl, rationality
• And finally my blog, I try to share surprising information, cogsci/relationships/computer science/math

gwern posts on google+ and Kaj Sotala posts interesting stuff on Facebook. I also subscribe to a number of journal's table of contents via this site to keep up with research and some stuff on arxiv.

Rational thinking against fear in a TED talk by (ex) astronaut Chris Hadfield. Has anyone else seen it? I really enjoyed it, in particular the spider example.

Did you mean to say continuous bijections? Obviously adding two points wouldn't change the cardinality of an infinite set, but "easy to compute" might change.

Oh, saying A,B,C,D are in [0,1] restricts quite a bit. It eliminates distributions with support over all the reals

???

There are easy to compute bijections from R to [0,1], etc.

The Bayesian approach to this problem uses an hierarchical distribution with two levels: one specifying the distribution p[A,B,C,D | X] in terms of some parameter vector X, and the other specifying the distribution p[X]

Yes, parametric Bayes does this. I am giving you a problem where you can't write down p(A,B,C,D | X) explicitly and then asking you to solve something frequentists are quite happy solving. Yes I am aware I can do a prior for this in the discrete case. I am sure a paper will come of it eventually.

Latent variables are still a pain, though.

The whole point of things like the beautiful distribution is you don't have to deal with latent variables. By the way the reason to think about H1 is that it represents all independences over A,B,C,D in this latent variable DAG:

A <- u1 -> B <- u2 -> C <- u3 -> D <- u4 -> A

where we marginalize out the ui variables.

which can indeed be written quite elegantly as an exponential family distribution with features for each clique in the graph

I think you might be confusing undirected and bidirected graph models. The former form linear exponential families and can be parameterized via cliques, the latter form curved exponential families, and can be parameterized via connected sets.

If I may add something to (2) (and (3), too) I'd say to be concise and not wander too far: keep the focus and don't waste time. Moreover I think that a contribution, let it be a comment or a main argument, is much more interesting if it's different from what it has been already said before. I often hear people asking questions or offering arguments that have shown up before, without providing any new insight. Basically you could say "Listen before you speak".

Hi everyone, I'm labachevskij. I'm a long time lurker on this site, attracted by (IIRC) Bayesian Decision Theory. I'm completing my PhD studies in Maths, but I have also been caught by HPMOR, which is proving a huge source of procrastination (I'm reading it again for the third time). I'm also on my way with the reading of the sequences.

Welcome labachevskij!

What part of Math are you focusing on?

Hi everyone, I'm labachevskij. I'm a long time lurker on this site, attracted by (IIRC) Bayesian Decision Theory. I'm completing my PhD studies in Maths, but I have also been caught by HPMOR, which is proving a huge source of procrastination (I'm reading it again for the third time). I'm also on my way with the reading of the sequences.