This shows you the differences between two versions of the page.
Next revision | Previous revision | ||
papers:bottou-still-2004 [2006/04/12 19:14] 127.0.0.1 (old revision restored) |
papers:bottou-still-2004 [2018/12/06 10:00] (current) leonb |
||
---|---|---|---|
Line 1: | Line 1: | ||
===== Geometric Clustering Using the Information Bottleneck Method ===== | ===== Geometric Clustering Using the Information Bottleneck Method ===== | ||
+ | // | ||
+ | We argue that K--means and deterministic annealing algorithms for geometric | ||
+ | clustering can be derived from the more general Information Bottleneck | ||
+ | approach. If we cluster the identities of data points to preserve | ||
+ | information about their location, the set of optimal solutions is massively | ||
+ | degenerate. But if we treat the equations that define the optimal solution | ||
+ | as an iterative algorithm, then a set of " | ||
+ | solutions with the desired geometrical properties. In addition to conceptual | ||
+ | unification, | ||
+ | robust than classic algorithms. | ||
<box 99% orange> | <box 99% orange> | ||
- | Susanne Still, William Bialek and Léon Bottou: Geometric Clustering Using the Information Bottleneck Method, | + | Susanne Still, William Bialek and Léon Bottou: |
[[http:// | [[http:// | ||
Line 14: | Line 24: | ||
author = {Still, Susanne and Bialek, William and Bottou, L\' | author = {Still, Susanne and Bialek, William and Bottou, L\' | ||
title = {Geometric Clustering Using the Information Bottleneck Method}, | title = {Geometric Clustering Using the Information Bottleneck Method}, | ||
- | booktitle = {Advances in Neural Information Processing Systems 16}, | + | booktitle = {Advances in Neural Information Processing Systems 16 (NIPS 2003)}, |
editor = {Thrun, Sebastian and Saul, Lawrence and Bernhard {Sch\" | editor = {Thrun, Sebastian and Saul, Lawrence and Bernhard {Sch\" | ||
publisher = {MIT Press}, | publisher = {MIT Press}, |