Active Learning a Convex Body in Low Dimensions

03/08/2019
by   Sariel Har-Peled, et al.
0

Consider a set P ⊆R^d of n points, and a convex body C provided via a separation oracle. The task at hand is to decide for each point of P if it is in C. We show that one can solve this problem in two and three dimensions using O( index(P) n) queries, where index(P) is the largest subset of points of P in convex position. Furthermore, we show that in two dimensions one can solve this problem using O( price(P,C) ^2 n ) oracle queries, where price(P, C) is the minimal number of queries that any algorithm for this specific instance requires.

READ FULL TEXT
research
12/08/2017

How to Net a Convex Shape

We revisit the problem of building weak -nets for convex ranges over...
research
09/03/2018

Convex optimization using quantum oracles

We study to what extent quantum algorithms can speed up solving convex o...
research
09/08/2022

Active Learning of Classifiers with Label and Seed Queries

We study exact active learning of binary and multiclass classifiers with...
research
01/31/2021

Exact Recovery of Clusters in Finite Metric Spaces Using Oracle Queries

We investigate the problem of exact cluster recovery using oracle querie...
research
12/23/2020

Improved Algorithm for Computing the Maximum-volume Bichromatic Separating Box

We consider the problem of computing the largest-area bichromatic separa...
research
05/06/2022

Finding Points in Convex Position in Density-Restricted Sets

For a finite set A⊂ℝ^d, let Δ(A) denote the spread of A, which is the ra...
research
02/15/2023

Two-sided convexity testing with certificates

We revisit the problem of property testing for convex position for point...

Please sign up or login with your details

Forgot password? Click here to reset