Active Learning and Best-Response Dynamics

TL;DR

This paper explores how local communication and best-response dynamics among noisy sensors can effectively denoise data, enabling accurate learning with minimal queries, combining game theory and active learning techniques.

Contribution

It introduces a novel approach combining game-theoretic dynamics with active learning to improve data denoising and reduce query complexity in sensor networks.

Findings

Denoising via best-response dynamics can be effective in noisy sensor settings.

Combining dynamics with active learning achieves low error with few queries.

Experimental results outperform traditional passive and active learning methods.

Abstract

We examine an important setting for engineered systems in which low-power distributed sensors are each making highly noisy measurements of some unknown target function. A center wants to accurately learn this function by querying a small number of sensors, which ordinarily would be impossible due to the high noise rate. The question we address is whether local communication among sensors, together with natural best-response dynamics in an appropriately-defined game, can denoise the system without destroying the true signal and allow the center to succeed from only a small number of active queries. By using techniques from game theory and empirical processes, we prove positive (and negative) results on the denoising power of several natural dynamics. We then show experimentally that when combined with recent agnostic active learning algorithms, this process can achieve low error from very few queries, performing substantially better than active or passive learning without these denoising dynamics as well as passive learning with denoising.