Online algorithm for aggregating experts’ predictions with unbounded quadratic loss

2020-10-01

Russian Mathematical Surveys

AI Summary

This paper studies online expert aggregation under unbounded quadratic loss—a setting where conventional methods require prior knowledge of the loss upper bound, while our work proposes the first adaptive algorithm that operates without such a bound. Methodologically, we design an exponential-weighting-based dynamic weight update scheme, integrating online learning with adaptive truncation to ensure robustness against highly volatile losses. We theoretically establish that the algorithm achieves the optimal sublinear regret bound $O(sqrt{T log N})$. Empirically, it significantly outperforms classical weighted averaging and existing adaptive approaches on benchmark tasks featuring unbounded and rapidly varying losses. The key contribution is the elimination of dependence on a known loss bound, thereby enabling a more general and robust aggregation framework for online prediction in real-world dynamic environments.

Technology Category

• Machine Learning: Online Learning & Bandits
• Multiagent Systems: Adversarial Agents
• Search and Optimization: Learning to Search

Application Category

• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI

Abstract

We consider the problem of online aggregation of expert predictions with the quadratic loss function. We propose an algorithm for aggregating expert predictions which does not require a prior knowledge of the upper bound on the losses. The algorithm is based on the exponential reweighing of expert losses.

Problem

• Online aggregation of expert predictions
• Quadratic loss function without prior bounds
• Algorithm using exponential reweighing of losses

Innovation

• Online algorithm for expert prediction aggregation
• Handles unbounded quadratic loss without prior knowledge
• Uses exponential reweighting of expert losses