Noisy Generalized Binary Search
نویسنده
چکیده
This paper addresses the problem of noisy Generalized Binary Search (GBS). GBS is a well-known greedy algorithm for determining a binary-valued hypothesis through a sequence of strategically selected queries. At each step, a query is selected that most evenly splits the hypotheses under consideration into two disjoint subsets, a natural generalization of the idea underlying classic binary search. GBS is used in many applications, including fault testing, machine diagnostics, disease diagnosis, job scheduling, image processing, computer vision, and active learning. In most of these cases, the responses to queries can be noisy. Past work has provided a partial characterization of GBS, but existing noise-tolerant versions of GBS are suboptimal in terms of query complexity. This paper presents an optimal algorithm for noisy GBS and demonstrates its application to learning multidimensional threshold functions.
منابع مشابه
Organizing and Searching the World Wide Web of Facts - Step One: The One-Million Fact Extraction Challenge
Due to the inherent difficulty of processing noisy text, the potential of the Web as a decentralized repository of human knowledge remains largely untapped during Web search. The access to billions of binary relations among named entities would enable new search paradigms and alternative methods for presenting the search results. A first concrete step towards building large searchable repositor...
متن کاملThe Bayesian Learner is Optimal for Noisy Binary Search (and Pretty Good for Quantum as Well)
We use a Bayesian approach to optimally solve problems in noisy binary search. We deal with two variants: • Each comparison is erroneous with independent probability 1− p. • At each stage k comparisons can be performed in parallel and a noisy answer is returned. We present a (classical) algorithm which solves both variants optimally (with respect to p and k), up to an additive term of O(loglog ...
متن کاملNear-Optimal Bayesian Active Learning with Noisy Observations
We tackle the fundamental problem of Bayesian active learning with noise, where we need to adaptively select from a number of expensive tests in order to identify an unknown hypothesis sampled from a known prior distribution. In the case of noise–free observations, a greedy algorithm called generalized binary search (GBS) is known to perform near–optimally. We show that if the observations are ...
متن کاملAlgorithms and Data Structures in the noisy comparison model and applications
In contrast to classical computational models where every operation gives the correct answer always, we consider models with noise introduced in the operations they perform. In particular we look at the scenario when comparisions between elements turns noisy, i.e, gives the wrong result with a small probability. In this setting, we present existing algorithms in literature for binary search and...
متن کاملP´olya Urn Models and Connections to Random Trees: A Review
This paper reviews P´olya urn models and their connection to random trees. Basic results are presented, together with proofs that underly the historical evolution of the accompanying thought process. Extensions and generalizations are given according to chronology: • P´olya-Eggenberger’s urn • Bernard Friedman’s urn • Generalized P´olya urns • Extended urn schemes • Invertible urn schemes ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2009