Abstract | ||
---|---|---|
We consider the problem of active sequential hypothesis testing where a Bayesian decision maker must infer the true hypothesis from a set of hypotheses. The decision maker may choose for a set of actions, where the outcome of an action is corrupted by independent noise. In this paper we consider a special case where the decision maker has limited knowledge about the distribution of observations for each action, in that only a binary value is observed. Our objective is to infer the true hypothesis with low error, while minimizing the number of action sampled. Our main results include the derivation of a lower bound on sample size for our system under limited knowledge and the design of an active learning policy that matches this lower bound and outperforms similar known algorithms. |
Year | Venue | Field |
---|---|---|
2017 | ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 30 (NIPS 2017) | Mathematical optimization,Active learning,Upper and lower bounds,Computer science,Artificial intelligence,Sequential analysis,Sample size determination,Statistical hypothesis testing,Machine learning,Decision maker,Special case,Bayesian probability |
DocType | Volume | ISSN |
Conference | 30 | 1049-5258 |
Citations | PageRank | References |
0 | 0.34 | 3 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Fabio Cecchi | 1 | 21 | 4.09 |
Nidhi Hegde | 2 | 234 | 20.41 |