In machine learning, we are obsessed with datasets and metrics: progress in
areas as diverse as natural language understanding, object recognition, and
reinforcement learning is tracked by numerical scores on agreed-upon benchmarks.
Suppose that we want to construct subsets $S_1, \ldots, S_m \subseteq
\{1,\ldots,n\}$ with the following properties:
1. $|S_i| \geq k$ for all $i$
2. $|S_i \cap S_
I've spent much of the last few days reading various ICML papers and I find
there's a few pieces of feedback that I give consistently across several papers.
I&
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
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^