OEUVRE: OnlinE Unbiased Variance-Reduced loss Estimation

TL;DR

OEUVRE is a new online loss estimator that efficiently updates and adapts in real-time, providing reliable estimates with theoretical guarantees and strong empirical performance across various tasks.

Contribution

It introduces OEUVRE, a recursive, hyperparameter-adaptive loss estimator with proven consistency and convergence, applicable to many online learning algorithms.

Findings

OEUVRE achieves comparable or better accuracy than existing estimators.

The method effectively adapts hyperparameters without ground truth.

OEUVRE demonstrates strong theoretical guarantees and practical performance.

Abstract

Online learning algorithms continually update their models as data arrive, making it essential to accurately estimate the expected loss at the current time step. The prequential method is an effective estimation approach which can be practically deployed in various ways. However, theoretical guarantees have previously been established under strong conditions on the algorithm, and practical algorithms have hyperparameters which require careful tuning. We introduce OEUVRE, an estimator that evaluates each incoming sample on the function learned at the current and previous time steps, recursively updating the loss estimate in constant time and memory. We use algorithmic stability, a property satisfied by many popular online learners, for optimal updates and prove consistency, convergence rates, and concentration bounds for our estimator. We design a method to adaptively tune OEUVRE's hyperparameters and test it across diverse online and stochastic tasks. We observe that OEUVRE matches or outperforms other estimators even when their hyperparameters are tuned with oracle access to ground truth.