Online k-means Clustering

09/15/2019
by   Vincent Cohen-Addad, et al.
6

We study the problem of online clustering where a clustering algorithm has to assign a new point that arrives to one of k clusters. The specific formulation we use is the k-means objective: At each time step the algorithm has to maintain a set of k candidate centers and the loss incurred is the squared distance between the new point and the closest center. The goal is to minimize regret with respect to the best solution to the k-means objective (C) in hindsight. We show that provided the data lies in a bounded region, an implementation of the Multiplicative Weights Update Algorithm (MWUA) using a discretized grid achieves a regret bound of Õ(√(T)) in expectation. We also present an online-to-offline reduction that shows that an efficient no-regret online algorithm (despite being allowed to choose a different set of candidate centres at each round) implies an offline efficient algorithm for the k-means problem. In light of this hardness, we consider the slightly weaker requirement of comparing regret with respect to (1 + ϵ) C and present a no-regret algorithm with runtime O(T(poly(log(T),k,d,1/ϵ)^k(d+O(1))). Our algorithm is based on maintaining an incremental coreset and an adaptive variant of the MWUA. We show that naïve online algorithms, such as Follow The Leader, fail to produce sublinear regret in the worst case. We also report preliminary experiments with synthetic and real-world data.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/13/2023

Achieving Better Regret against Strategic Adversaries

We study online learning problems in which the learner has extra knowled...
research
03/14/2016

Online Isotonic Regression

We consider the online version of the isotonic regression problem. Given...
research
06/08/2021

Efficient Online Learning for Dynamic k-Clustering

We study dynamic clustering problems from the perspective of online lear...
research
02/25/2019

Improved Algorithm on Online Clustering of Bandits

We generalize the setting of online clustering of bandits by allowing no...
research
02/25/2017

Efficient Online Bandit Multiclass Learning with Õ(√(T)) Regret

We present an efficient second-order algorithm with Õ(1/η√(T)) regret fo...
research
10/20/2020

POND: Pessimistic-Optimistic oNline Dispatch

This paper considers constrained online dispatch with unknown arrival, r...
research
02/01/2016

A Quasi-Bayesian Perspective to Online Clustering

When faced with high frequency streams of data, clustering raises theore...

Please sign up or login with your details

Forgot password? Click here to reset