Abstract
Consider a set \(P\subseteq \mathbb {R}^d\) 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 \(C\) using the fewest number of oracle queries. We show that one can solve this problem in two and three dimensions using queries, where is the size of the largest subset of points of \(P\) in convex position. In 2D, we provide an algorithm that efficiently generates these adaptive queries. Furthermore, we show that in two dimensions one can solve this problem using oracle queries, where is a lower bound on the minimum number of queries that any algorithm for this specific instance requires. Finally, we consider other variations on the problem, such as using the fewest number of queries to decide if \(C\) contains all points of \(P\). As an application of the above, we show that the discrete geometric median of a point set P in \(\mathbb {R}^2\) can be computed in expected time.
Similar content being viewed by others
References
Ambrus, G., Bárány, I.: Longest convex chains. Rand. Struct. Algorithm 35(2), 137–162 (2009). https://doi.org/10.1002/rsa.20269
Angluin, D.: Queries and concept learning. Mach. Learn. 2(4), 319–342 (1987). https://doi.org/10.1007/BF00116828
Bárány, I.: A generalization of Carathéodory’s theorem. Discrete Math. 40(2–3), 141–152 (1982). https://doi.org/10.1016/0012-365X(82)90115-7
Bárány, I., Füredi, Z.: Computing the volume is difficulte. Discrete Comput. Geom. 2, 319–326 (1987). https://doi.org/10.1007/BF02187886
Chan, T.M.: An optimal randomized algorithm for maximum Tukey depth. In: J.I. Munro (ed.) Proceedings of 15th ACM-SIAM Symposium Discrete Algs. (SODA), pp. 430–436. SIAM (2004). URL http://dl.acm.org/citation.cfm?id=982792.982853
Clarkson, K.L., Shor, P.W.: Applications of random sampling in computational geometry, II. Discrete Comput. Geom. 4, 387–421 (1989). https://doi.org/10.1007/BF02187740
Cohen, M.B., Lee, Y.T., Miller, G.L., Pachocki, J., Sidford, A.: Geometric median in nearly linear time. In: D. Wichs, Y. Mansour (eds.) Proc. 48th ACM Sympos. Theory Comput. (STOC), pp. 9–21. ACM (2016). https://doi.org/10.1145/2897518.2897647
Cohn, D.A., Atlas, L.E., Ladner, R.E.: Improving generalization with active learning. Mach. Learn. 15(2), 201–221 (1994). https://doi.org/10.1007/BF00993277
Dudley, R.M.: Metric entropy of some classes of sets with differentiable boundaries. J. Approx. Theory 10(3), 227–236 (1974). https://doi.org/10.1016/0021-9045(74)90120-8
Ezra, E., Sharir, M.: A nearly quadratic bound for point-location in hyperplane arrangements, in the linear decision tree model. Discrete Comput. Geom. 61(4), 735–755 (2019). https://doi.org/10.1007/s00454-018-0043-8
Ferrera, J.: An Introduction to Nonsmooth Analysis. Academic Press, Boston (2013). https://doi.org/10.1016/C2013-0-15234-8
Guo, Y., Greiner, R.: Optimistic active-learning using mutual information. In: Proceedings of 20th International Joint Conference on AI (IJCAI), pp. 823–829 (2007). URL http://ijcai.org/Proceedings/07/Papers/132.pdf
Har-Peled, S., Jones, M., Rahul, S.: An animation of the greedy classification algorithm in 2d. URL https://www.youtube.com/watch?v=IZX0VQdIgNA
Har-Peled, S., Jones, M., Rahul, S.: Active learning a convex body in low dimensions. In: A. Czumaj, A. Dawar, E. Merelli (eds.) Proc. 47th Int. Colloq. Automata Lang. Prog. (ICALP), Leibniz International Proceedings in Informatics (LIPIcs), vol. 168, pp. 64:1–64:17. Schloss Dagstuhl–Leibniz-Zentrum für Informatik, Dagstuhl, Germany (2020). https://doi.org/10.4230/LIPIcs.ICALP.2020.64. URL https://drops.dagstuhl.de/opus/volltexte/2020/12471
Har-Peled, S., Kumar, N., Mount, D.M., Raichel, B.: Space exploration via proximity search. Discrete Comput. Geom. 56(2), 357–376 (2016). https://doi.org/10.1007/s00454-016-9801-7
Haussler, D., Welzl, E.: \(\varepsilon \)-nets and simplex range queries. Discrete Comput. Geom. 2, 127–151 (1987). https://doi.org/10.1007/BF02187876
Kane, D.M., Lovett, S., Moran, S., Zhang, J.: Active classification with comparison queries. In: Proc. 58th Annu. IEEE Sympos. Found. Comput. Sci. (FOCS), pp. 355–366 (2017). https://doi.org/10.1109/FOCS.2017.40
Kedem, K., Livne, R., Pach, J., Sharir, M.: On the union of Jordan regions and collision-free translational motion amidst polygonal obstacles. Discrete Comput. Geom. 1(1), 59–71 (1986). https://doi.org/10.1007/BF02187683
Kupavskii, A.: The vc-dimension of k-vertex d-polytopes. CoRR arXiv:abs/2004.04841 (2020)
Matoušek, J.: Lectures on Discrete Geometry, Grad. Text in Math., vol. 212. Springer (2002). https://doi.org/10.1007/978-1-4613-0039-7/. URL http://kam.mff.cuni.cz/~matousek/dg.html
Matoušek, J., Wagner, U.: New constructions of weak epsilon-nets. In: Proceedings of the Nineteenth Annual Symposium on Computational Geometry, pp. 129–135. ACM (2003)
Mehlhorn, K., Näher, S.: Dynamic fractional cascading. Algorithmica 5(2), 215–241 (1990). https://doi.org/10.1007/BF01840386
Panahi, F., Adler, A., van der Stappen, A.F., Goldberg, K.: An efficient proximity probing algorithm for metrology. In: Int. Conf. on Automation Science and Engineering, CASE 2013, pp. 342–349 (2013). https://doi.org/10.1109/CoASE.2013.6653995
Preparata, F.P., Shamos, M.I.: Computational Geometry: An Introduction. Texts and Monographs in Computer Science. Springer (1985). https://doi.org/10.1007/978-1-4612-1098-6
Rubin, N.: An improved bound for weak epsilon-nets in the plane. In: M. Thorup (ed.) Proc. 59th Annu. IEEE Sympos. Found. Comput. Sci. (FOCS), pp. 224–235. IEEE Computer Society (2018). https://doi.org/10.1109/FOCS.2018.00030
Settles, B.: Active learning literature survey. Tech. Rep. #1648, Computer Science, Univ. Wisconsin, Madison (2009). URL https://minds.wisconsin.edu/bitstream/handle/1793/60660/TR1648.pdf?sequence=1&isAllowed=y
Vapnik, V.N., Chervonenkis, A.Y.: On the uniform convergence of relative frequencies of events to their probabilities. Theory Probab. Appl. 16, 264–280 (1971)
Weil, W. (ed.): Random Polytopes, Convex Bodies, and Approximation, pp. 77–118. Springer Berlin Heidelberg, Berlin, Heidelberg (2007). https://doi.org/10.1007/978-3-540-38175-4_2
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
A preliminary version appeared in the Proceedings of the 47th International Colloquium on Automata Languages and Programming (ICALP 2020) [14].
Sariel Har-Peled is supported in part by NSF AF Award CCF-1907400.
Expected Separation Price for Random Points
Expected Separation Price for Random Points
We first extend the notion of separation price (see Sect. 3.1) to higher dimensions. For a closed convex d-dimensional polytope F, we let \(f_k(F)\) denote the number of k-dimensional faces of F.
Definition 6
(Separation price in higher dimensions) Let \(P\) be a set of points and \(C\) be a convex body in \(\mathbb {R}^d\). The inner fence \(F_{\mathrm {in}}\) is a closed convex d-dimensional polytope with the minimum number of vertices, such that \(F_{\mathrm {in}}\subseteq C\) and \(C\cap P= F_{\mathrm {in}}\cap P\). Similarly, the outer fence \(F_{\mathrm {out}}\) is a closed convex d-dimensional polytope with the minimum number of facets, such that \(C\subseteq F_{\mathrm {out}}\) and \(C\cap P= F_{\mathrm {out}}\cap P\). The separation price is defined as .
By extending the argument of Lemma 13 to use Definition 6, one can prove the following.
Lemma 27
Given a point set \(P\) and a convex body \(C\) in \(\mathbb {R}^d\), any algorithm that classifies the points of \(P\) in relation to \(C\), must perform at least separation oracle queries.
Informally, for any fixed convex body \(C\) and a set of n points \(P\) chosen uniformly at random from the unit cube, the separation price is sublinear (approaching linear as the dimension increases).
Lemma 28
Let \(P\) be a set of n points chosen uniformly at random from the unit cube \([0,1]^d\), and let \(C\) be a convex body in \(\mathbb {R}^d\), with \(\textsf {vol}(C) \ge c\) for some constant \(c \le 1\). Then , where O hides constants that depend on d and \(C\).
Proof
It is known that for convex bodies \(C\), the expected number of vertices of the convex hull of \(P\cap C\) is \(O(n^{1 - 2/(d+1)})\). Indeed, since \(\textsf {vol}(C) \ge c\), the expected number of points of \(P\) that fall inside \(C\) is \(m = \varTheta (n)\) (and these bounds hold with high probability by applying any Chernoff-like bound). It is known that for m points chosen uniformly at random from \(C\), the expected size of the convex hull of points inside \(C\) is \(O(m^{1 - 2/(d+1)}) = O(n^{1 - 2/(d+1)})\) [28]. This readily implies that .
To bound , we apply a result of Dudley [9] which states the following. Given a convex body \(C\) and a parameter \(\varepsilon > 0\), there exists a convex body D, which is a polytope formed by the intersection of \(O(\varepsilon ^{-(d-1)/2})\) halfspaces, such that \(C\subseteq D \subseteq (1+\varepsilon )C\), where .
We claim that the number of points of \(P\) that fall inside \(D \setminus C\), plus the number of halfspaces defining D, is an upper bound on the size of the outer fence. Indeed, for each point \(p\) that falls in inside \(D \setminus C\), let \(q\) be its nearest neighbor in \(C\) (naturally \(q\) lies on \(\partial C\)). Let be the hyperplane that is perpendicular to the segment \(pq\) and passing through the midpoint of pq. Next, let be the halfspace bounded by such that . If H is the collection of \(O(\varepsilon ^{-(d-1)/2})\) halfspaces defining D, then it is easy to see that the polytope defined by
separates the boundary of \(C\) from \(P\setminus C\) (i.e., it is an outer fence). See the figure below.
We now bound the size of this inner fence. Since \(\textsf {vol}(D) - \textsf {vol}(C) \le \textsf {vol}((1+\varepsilon )C) - \textsf {vol}(C) \le O(\varepsilon )\), we have that . Combining both inequalities,
Choose \(\varepsilon = 1/n^{2/(d+1)}\) to balance both terms, so that . \(\square \)
The next Lemma shows that the bound of Lemma 28 is tight in the worst case.
Lemma 29
Let \(P\) be a set of n points chosen uniformly at random from the hypercube \([-2,2]^d\), and let \(C\) be a unit radius ball centered at the origin. Then , where \(\varOmega \) hides constants depending on d.
Proof
For a parameter \(\delta \) to be chosen, let \(Q \subseteq \partial C\) be a maximal set of points such that:
-
(i)
for any \(p\in \partial C\), there is a point \(q\in Q\) such that \(\Vert p- q\Vert \le \delta \), and
-
(ii)
for any two points \(p, q\in Q\), \(\Vert p- q\Vert \ge \delta \).
Note that \(\left| {Q} \right| = \varOmega (1/\delta ^{d-1})\). For each \(p\in Q\), we let \(\gamma _{p}\) be the spherical cap that is “centered” at \(p\) (in the sense that the center of the base of \(\gamma _{p}\), \(p\), and the origin are collinear) and has base radius \(2\delta \). Let . By construction, the caps of \(\varGamma \) cover the surface of \(C\).
By setting \(\delta = 1/n^{1/(d+1)}\), we claim that for each cap \(\gamma \in \varGamma \), in expectation \(\varOmega (1)\) points of \(P\) fall inside \(\gamma \). This implies that there must be a vertex of the inner fence inside \(\gamma \), and this holds for all caps in \(\varGamma \). As such, the size of the inner fence is at least \(\left| {Q} \right| = \varOmega (1/\delta ^{d-1}) = \varOmega (n^{1 - 2/(d+1)})\).
To prove the claim, for all \(\gamma \in \varGamma \), we show that \(\textsf {vol}(\gamma ) = \varOmega (1/n)\), and hence . By construction, the cap has a polar angle of \(\theta = \varOmega (\delta )\). Indeed, we have that \(\theta \ge \sin (\theta ) = 2\delta \) for \(\theta \in [0,\pi /2]\) (which holds when n is sufficiently large). Let t denote the distance from the origin to the center of the base of \(\gamma \). Then the height h of the spherical cap is \(h = 1 - t = 1 - \cos (\theta ) \ge \theta ^2/6 = \varOmega (\delta ^2)\) (using the inequality \(\cos (x) \le 1 - x^2/6\)). Since the volume of the base of \(\gamma \) is \(\varOmega (\delta ^{d-1})\), we have that \(\textsf {vol}(\gamma ) = \varOmega (h \delta ^{d-1}) = \varOmega (\delta ^{d+1}) = \varOmega (1/n)\), as required. \(\square \)
Rights and permissions
About this article
Cite this article
Har-Peled, S., Jones, M. & Rahul, S. Active-Learning a Convex Body in Low Dimensions. Algorithmica 83, 1885–1917 (2021). https://doi.org/10.1007/s00453-021-00807-w
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00453-021-00807-w