The ABACOC Algorithm: a Novel Approach for Nonparametric Classification of Data Streams

TL;DR

The paper introduces ABACOC, a nonparametric, scalable, and parameterless algorithm for data stream classification that adapts locally to the complexity of the data, achieving high accuracy with bounded model size.

Contribution

It presents a novel adaptive nonparametric algorithm for data streams that balances model complexity and accuracy without prior knowledge of class labels or parameters.

Findings

State-of-the-art accuracy with bounded model size

Better performance than baselines at the same model size

Theoretical guarantees without stochastic assumptions

Abstract

Stream mining poses unique challenges to machine learning: predictive models are required to be scalable, incrementally trainable, must remain bounded in size (even when the data stream is arbitrarily long), and be nonparametric in order to achieve high accuracy even in complex and dynamic environments. Moreover, the learning system must be parameterless ---traditional tuning methods are problematic in streaming settings--- and avoid requiring prior knowledge of the number of distinct class labels occurring in the stream. In this paper, we introduce a new algorithmic approach for nonparametric learning in data streams. Our approach addresses all above mentioned challenges by learning a model that covers the input space using simple local classifiers. The distribution of these classifiers dynamically adapts to the local (unknown) complexity of the classification problem, thus achieving a good balance between model complexity and predictive accuracy. We design four variants of our approach of increasing adaptivity. By means of an extensive empirical evaluation against standard nonparametric baselines, we show state-of-the-art results in terms of accuracy versus model size. For the variant that imposes a strict bound on the model size, we show better performance against all other methods measured at the same model size value. Our empirical analysis is complemented by a theoretical performance guarantee which does not rely on any stochastic assumption on the source generating the stream.