In my previous post, “Latent Variables and Model Mis-specification
[https://jsteinhardt.wordpress.com/2017/01/10/latent-variables-and-model-mis-specification/]
”, I argued that while machine learning is good at optimizing accuracy on
observed signals, it has
Here is interesting linear algebra fact: let $A$ be an $n \times n$ matrix and
$u$ be a vector such that $u^{\top}A = \lambda u^{\top}$. Then for any matrix
$B$, $u^
Consider the following statements:
1. The shape with the largest volume enclosed by a given surface area is the
$n$-dimensional sphere.
2. A marginal or sum of log-concave distributions is log-concave.
3.
Machine learning is very good at optimizing predictions to match an observed
signal --- for instance, given a dataset of input images and labels of the
images (e.g. dog, cat, etc.), machine
In my post on where I plan to donate in 2016
[https://jsteinhardt.wordpress.com/2016/12/28/donations-for-2016/], I said that
I would set aside \$2000 for funding promising projects that I