Trong Nghia Hoang

Nonmyopic \(\epsilon\)-Bayes-Optimal Active Learning of Gaussian Processes

A fundamental issue in active learning of Gaussian processes is that of the exploration-exploitation trade-off. This paper presents a novel nonmyopic e-Bayes-optimal active learning (e-BAL) approach that jointly and naturally optimizes the trade-off. In contrast, existing works have primarily developed myopic/greedy algorithms or performed exploration and exploitation separately. To perform active learning in real time, we then propose an anytime algorithm based on e-BAL with performance guarantee and empirically demonstrate using synthetic and real-world datasets that, with limited budget, it outperforms the state-of-the-art algorithms.

Recent Advances in Scaling Up Gaussian Process Predictive Models for Large Spatiotemporal Data

The expressive power of Gaussian process (GP) models comes at a cost of poor scalability in the size of the data. To improve their scalability, this paper presents an overview of our recent progress in scaling up GP models for large spatiotemporally correlated data through parallelization on clusters of machines, online learning, and nonmyopic active sensing/learning.

Active learning is planning: nonmyopic ε-Bayes-optimal active learning of Gaussian processes

A fundamental issue in active learning of Gaussian processes is that of the exploration-exploitation trade-off. This paper presents a novel nonmyopic e-Bayes-optimal active learning (e-BAL) approach [4] that jointly optimizes the trade-off. In contrast, existing works have primarily developed greedy algorithms or performed exploration and exploitation separately. To perform active learning in real time, we then propose an anytime algorithm [4] based on e-BAL with performance guarantee and empirically demonstrate using a real-world dataset that, with limited budget, it outperforms the state-of-the-art algorithms.

Scalable Decision-Theoretic Coordination and Control for Real-time Active Multi-Camera Surveillance

This paper presents an overview of our novel decision-theoretic multi-agent approach for controlling and coordinating multiple active cameras in surveillance. In this approach, a surveillance task is modeled as a stochastic optimization problem, where the active cameras are controlled and coordinated to achieve the desired surveillance goal in presence of uncertainties. We enumerate the practical issues in active camera surveillance and discuss how these issues are addressed in our decision-theoretic approach. We focus on two novel surveillance tasks: maximize the number of targets observed in active cameras with guaranteed image resolution and to improve the fairness in observation of multiple targets. We discuss the overview of our novel decision-theoretic frameworks: Markov Decision Process and Partially Observable Markov Decision Process frameworks for coordinating active cameras in uncertain and partially occluded environments.