• Publications
  • Influence
A contextual-bandit approach to personalized news article recommendation
TLDR
This work model personalized recommendation of news articles as a contextual bandit problem, a principled approach in which a learning algorithm sequentially selects articles to serve users based on contextual information about the users and articles, while simultaneously adapting its article-selection strategy based on user-click feedback to maximize total user clicks. Expand
CAPTCHA: Using Hard AI Problems for Security
TLDR
This work introduces captcha, an automated test that humans can pass, but current computer programs can't pass; any program that has high success over a captcha can be used to solve an unsolved Artificial Intelligence (AI) problem; and provides several novel constructions of captchas, which imply a win-win situation. Expand
Approximately Optimal Approximate Reinforcement Learning
Cover trees for nearest neighbor
TLDR
A tree data structure for fast nearest neighbor operations in general n-point metric spaces (where the data set consists of n points) that shows speedups over the brute force search varying between one and several orders of magnitude on natural machine learning datasets. Expand
A Reductions Approach to Fair Classification
TLDR
The key idea is to reduce fair classification to a sequence of cost-sensitive classification problems, whose solutions yield a randomized classifier with the lowest (empirical) error subject to the desired constraints. Expand
Feature hashing for large scale multitask learning
TLDR
This paper provides exponential tail bounds for feature hashing and shows that the interaction between random subspaces is negligible with high probability, and demonstrates the feasibility of this approach with experimental results for a new use case --- multitask learning. Expand
Telling humans and computers apart automatically
How lazy cryptographers do AI.
Doubly Robust Policy Evaluation and Learning
TLDR
It is proved that the doubly robust approach uniformly improves over existing techniques, achieving both lower variance in value estimation and better policies, and is expected to become common practice. Expand
Multi-Label Prediction via Compressed Sensing
TLDR
It is shown that the number of subproblems need only be logarithmic in the total number of possible labels, making this approach radically more efficient than others. Expand
Search-based structured prediction
TLDR
Searn is an algorithm for integrating search and learning to solve complex structured prediction problems such as those that occur in natural language, speech, computational biology, and vision and comes with a strong, natural theoretical guarantee: good performance on the derived classification problems implies goodperformance on the structured prediction problem. Expand
...
1
2
3
4
5
...