Sequential mode estimation with oracle queries

Shah, D and Choudhury, T and Karamchandani, N and Gopalan, A (2020) Sequential mode estimation with oracle queries. In: AAAI 2020 - 34th AAAI Conference on Artificial Intelligence, 7 February - 12 February 2020, New York, pp. 5644-5651.

PDF AAAI_2020 - Published Version Restricted to Registered users only Download (563kB) | Request a copy

Abstract

We consider the problem of adaptively PAC-learning a probability distribution P's mode by querying an oracle for information about a sequence of i.i.d. samples X1, X2,... generated from P. We consider two different query models: (a) each query is an index i for which the oracle reveals the value of the sample Xi, (b) each query is comprised of two indices i and j for which the oracle reveals if the samples Xi and Xj are the same or not. For these query models, we give sequential mode-estimation algorithms which, at each time t, either make a query to the corresponding oracle based on past observations, or decide to stop and output an estimate for the distribution's mode, required to be correct with a specified confidence. We analyze the query complexity of these algorithms for any underlying distribution P, and derive corresponding lower bounds on the optimal query complexity under the two querying models.

Item Type:	Conference Paper
Publication:	AAAI 2020 - 34th AAAI Conference on Artificial Intelligence
Publisher:	AAAI press
Additional Information:	The copyright for this article belongs to AAAI press.
Keywords:	Computational complexity; Probability distributions, Lower bounds; Optimal query; PAC learning; Query complexity; Query model; Sequential mode; Underlying distribution, Artificial intelligence
Department/Centre:	Division of Electrical Sciences > Electrical Communication Engineering
Date Deposited:	07 Feb 2023 04:36
Last Modified:	07 Feb 2023 04:36
URI:	https://eprints.iisc.ac.in/id/eprint/79983

Actions (login required)

View Item