Efficient Learning of Simplices

Joseph Anderson, Navin Goyal, Luis Rademacher
Proceedings of the 26th Annual Conference on Learning Theory, PMLR 30:1020-1045, 2013.

Abstract

We show an efficient algorithm for the following problem: Given uniformly random points from an arbitrary n-dimensional simplex, estimate the simplex. The size of the sample and the number of arithmetic operations of our algorithm are polynomial in n. This answers a question of Frieze, Jerrum and Kannan Frieze et al. (1996). Our result can also be interpreted as efficiently learning the intersection of n + 1 half-spaces in R^n in the model where the intersection is bounded and we are given polynomially many uniform samples from it. Our proof uses the local search technique from Independent Component Analysis (ICA), also used by Frieze et al. (1996). Unlike these previous algorithms, which were based on analyzing the fourth moment, ours is based on the third moment. We also show a direct connection between the problem of learning a simplex and ICA: a simple randomized reduction to ICA from the problem of learning a simplex. The connection is based on a known representation of the uniform measure on a simplex. Similar representations lead to a reduction from the problem of learning an affine transformation of an n-dimensional l_p ball to ICA.

Cite this Paper


BibTeX
@InProceedings{pmlr-v30-Anderson13, title = {Efficient Learning of Simplices}, author = {Anderson, Joseph and Goyal, Navin and Rademacher, Luis}, booktitle = {Proceedings of the 26th Annual Conference on Learning Theory}, pages = {1020--1045}, year = {2013}, editor = {Shalev-Shwartz, Shai and Steinwart, Ingo}, volume = {30}, series = {Proceedings of Machine Learning Research}, address = {Princeton, NJ, USA}, month = {12--14 Jun}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v30/Anderson13.pdf}, url = {https://proceedings.mlr.press/v30/Anderson13.html}, abstract = {We show an efficient algorithm for the following problem: Given uniformly random points from an arbitrary n-dimensional simplex, estimate the simplex. The size of the sample and the number of arithmetic operations of our algorithm are polynomial in n. This answers a question of Frieze, Jerrum and Kannan Frieze et al. (1996). Our result can also be interpreted as efficiently learning the intersection of n + 1 half-spaces in R^n in the model where the intersection is bounded and we are given polynomially many uniform samples from it. Our proof uses the local search technique from Independent Component Analysis (ICA), also used by Frieze et al. (1996). Unlike these previous algorithms, which were based on analyzing the fourth moment, ours is based on the third moment. We also show a direct connection between the problem of learning a simplex and ICA: a simple randomized reduction to ICA from the problem of learning a simplex. The connection is based on a known representation of the uniform measure on a simplex. Similar representations lead to a reduction from the problem of learning an affine transformation of an n-dimensional l_p ball to ICA.} }
Endnote
%0 Conference Paper %T Efficient Learning of Simplices %A Joseph Anderson %A Navin Goyal %A Luis Rademacher %B Proceedings of the 26th Annual Conference on Learning Theory %C Proceedings of Machine Learning Research %D 2013 %E Shai Shalev-Shwartz %E Ingo Steinwart %F pmlr-v30-Anderson13 %I PMLR %P 1020--1045 %U https://proceedings.mlr.press/v30/Anderson13.html %V 30 %X We show an efficient algorithm for the following problem: Given uniformly random points from an arbitrary n-dimensional simplex, estimate the simplex. The size of the sample and the number of arithmetic operations of our algorithm are polynomial in n. This answers a question of Frieze, Jerrum and Kannan Frieze et al. (1996). Our result can also be interpreted as efficiently learning the intersection of n + 1 half-spaces in R^n in the model where the intersection is bounded and we are given polynomially many uniform samples from it. Our proof uses the local search technique from Independent Component Analysis (ICA), also used by Frieze et al. (1996). Unlike these previous algorithms, which were based on analyzing the fourth moment, ours is based on the third moment. We also show a direct connection between the problem of learning a simplex and ICA: a simple randomized reduction to ICA from the problem of learning a simplex. The connection is based on a known representation of the uniform measure on a simplex. Similar representations lead to a reduction from the problem of learning an affine transformation of an n-dimensional l_p ball to ICA.
RIS
TY - CPAPER TI - Efficient Learning of Simplices AU - Joseph Anderson AU - Navin Goyal AU - Luis Rademacher BT - Proceedings of the 26th Annual Conference on Learning Theory DA - 2013/06/13 ED - Shai Shalev-Shwartz ED - Ingo Steinwart ID - pmlr-v30-Anderson13 PB - PMLR DP - Proceedings of Machine Learning Research VL - 30 SP - 1020 EP - 1045 L1 - http://proceedings.mlr.press/v30/Anderson13.pdf UR - https://proceedings.mlr.press/v30/Anderson13.html AB - We show an efficient algorithm for the following problem: Given uniformly random points from an arbitrary n-dimensional simplex, estimate the simplex. The size of the sample and the number of arithmetic operations of our algorithm are polynomial in n. This answers a question of Frieze, Jerrum and Kannan Frieze et al. (1996). Our result can also be interpreted as efficiently learning the intersection of n + 1 half-spaces in R^n in the model where the intersection is bounded and we are given polynomially many uniform samples from it. Our proof uses the local search technique from Independent Component Analysis (ICA), also used by Frieze et al. (1996). Unlike these previous algorithms, which were based on analyzing the fourth moment, ours is based on the third moment. We also show a direct connection between the problem of learning a simplex and ICA: a simple randomized reduction to ICA from the problem of learning a simplex. The connection is based on a known representation of the uniform measure on a simplex. Similar representations lead to a reduction from the problem of learning an affine transformation of an n-dimensional l_p ball to ICA. ER -
APA
Anderson, J., Goyal, N. & Rademacher, L.. (2013). Efficient Learning of Simplices. Proceedings of the 26th Annual Conference on Learning Theory, in Proceedings of Machine Learning Research 30:1020-1045 Available from https://proceedings.mlr.press/v30/Anderson13.html.

Related Material