Coarse-Refinement Dilemma: On Generalization Bounds for Data Clustering

11/13/2019
by   Yule Vaz, et al.
13

The Data Clustering (DC) problem is of central importance for the area of Machine Learning (ML), given its usefulness to represent data structural similarities from input spaces. Differently from Supervised Machine Learning (SML), which relies on the theoretical frameworks of the Statistical Learning Theory (SLT) and the Algorithm Stability (AS), DC has scarce literature on general-purpose learning guarantees, affecting conclusive remarks on how those algorithms should be designed as well as on the validity of their results. In this context, this manuscript introduces a new concept, based on multidimensional persistent homology, to analyze the conditions on which a clustering model is capable of generalizing data. As a first step, we propose a more general definition of DC problem by relying on Topological Spaces, instead of metric ones as typically approached in the literature. From that, we show that the DC problem presents an analogous dilemma to the Bias-Variance one, which is here referred to as the Coarse-Refinement (CR) dilemma. CR is intended to clarify the contrast between: (i) highly-refined partitions and the clustering instability (overfitting); and (ii) over-coarse partitions and the lack of representativeness (underfitting); consequently, the CR dilemma suggests the need of a relaxation of Kleinberg's richness axiom. Experimental results were used to illustrate that multidimensional persistent homology support the measurement of divergences among DC models, leading to a consistency criterion.

READ FULL TEXT

page 24

page 26

page 27

page 28

page 29

page 30

page 31

page 42

08/02/2022

Sequents, barcodes, and homology

We consider the problem of generating hypothesis from data based on idea...
04/15/2019

Single Machine Graph Analytics on Massive Datasets Using Intel Optane DC Persistent Memory

Intel Optane DC Persistent Memory is a new kind of byte-addressable memo...
06/04/2021

Manifold-Aware Deep Clustering: Maximizing Angles between Embedding Vectors Based on Regular Simplex

This paper presents a new deep clustering (DC) method called manifold-aw...
06/27/2021

Machine Learning Detection Algorithm for Large Barkhausen Jumps in Cluttered Environment

Modern magnetic sensor arrays conventionally utilize state of the art lo...
01/13/2022

Persistent Extension and Analogous Bars: Data-Induced Relations Between Persistence Barcodes

A central challenge in topological data analysis is the interpretation o...
08/14/2017

DC-Prophet: Predicting Catastrophic Machine Failures in DataCenters

When will a server fail catastrophically in an industrial datacenter? Is...
10/20/2021

Transferring Reinforcement Learning for DC-DC Buck Converter Control via Duty Ratio Mapping: From Simulation to Implementation

Reinforcement learning (RL) control approach with application into power...