L. Ungar

activity

20092026

most citedProbabilistic Models for Unified Collaborative and Content-Based Recommendation in Sparse-Data Environments

443 citations · 867 across the 33 of their papers we have counts for

collaborators

Showing 2015Show all

2 papers · 1 filter

math.ST2015★ 15 cited

A Risk Ratio Comparison of $l_{0}$ and $l_{1}$ Penalized Regression

Kory D. Johnson, Dongyu Lin, Lyle H. Ungar +2

There has been an explosion of interest in using $l_{1}$ -regularization in place of $l_{0}$ -regularization for feature selection. We present theoretical results showing that while $l_1…

stat.ME2015

Partial Information Framework: Model-Based Aggregation of Estimates from Diverse Information Sources

Ville A. Satopää, Shane T. Jensen, Robin Pemantle +1

Prediction polling is an increasingly popular form of crowdsourcing in which multiple participants estimate the probability or magnitude of some future event. These estimates are t…

A Risk Ratio Comparison of l0​ and l1​ Penalized Regression

Partial Information Framework: Model-Based Aggregation of Estimates from Diverse Information Sources

A Risk Ratio Comparison of $l_{0}$ and $l_{1}$ Penalized Regression