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.
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.
| Original language | English |
|---|---|
| Title of host publication | 31st Conference on Advances in Neural Information Processing Systems (NIPS 2017), 4-9 December 2017, Long Beach, California |
| Pages | 4036-4044 |
| Number of pages | 9 |
| Publication status | Published - 2017 |