7k citations
- University of California, Santa BarbaraUS109 papers
- Microsoft Research (United Kingdom)GB53 papers
- ETH ZurichCH48 papers
- University of California, BerkeleyUS45 papers
- University of Maryland, College ParkUS44 papers
- Carnegie Mellon UniversityUS42 papers
- Stanford UniversityUS40 papers
- University of WashingtonUS38 papers
- Cornell UniversityUS33 papers
- Princeton UniversityUS32 papers
- California Institute of TechnologyUS28 papers
- Microsoft Research New York City (United States)26 papers
5 papers · 2 filters
Fast Label Embeddings via Randomized Linear Algebra
Paul Mineiro, Nikos Karampatziakis
Many modern multiclass and multilabel problems are characterized by increasingly large output spaces. For these problems, label embeddings have been shown to be a useful primitive…
Near-Optimal Density Estimation in Near-Linear Time Using Variable-Width Histograms
Siu-On Chan, Ilias Diakonikolas, Rocco A. Servedio +1
Let be an unknown and arbitrary probability distribution over . We consider the problem of {\em density estimation}, in which a learning algorithm is given i.i.d. draws…
Online Learning with Composite Loss Functions
Ofer Dekel, Jian Ding, Tomer Koren +1
We study a new class of online learning problems where each of the online algorithm's actions is assigned an adversarial value, and the loss of the algorithm at each step is a know…
Statistical Decision Making for Optimal Budget Allocation in Crowd Labeling
Xi Chen, Qihang Lin, Dengyong Zhou
In crowd labeling, a large amount of unlabeled data instances are outsourced to a crowd of workers. Workers will be paid for each label they provide, but the labeling requester usu…
Counterfactual Estimation and Optimization of Click Metrics for Search Engines
Lihong Li, Shunbao Chen, Jim Kleban +1
Optimizing an interactive system against a predefined online metric is particularly challenging, when the metric is computed from user feedback such as clicks and payments. The key…