Adaptive Sampling for Convex Regression

arXiv: Learning, Volume abs/1808.04523, 2018.

Cited by: 1|Views55
EI

Abstract:

In this paper, we introduce the first principled adaptive-sampling procedure for learning a convex function in the $L_infty$ norm, a problem that arises often in the behavioral and social sciences. We present a function-specific measure of complexity and use it to prove that, for each convex function $f_{star}$, our algorithm nearly attai...More

Code:

Data:

Get fulltext within 24h
Bibtex
Your rating :
0

 

Tags
Comments