2019/05/29 by Ayman Boustati, Theodoros Damoulas, Boustati, Ayman +3 · 13 citations
Computer Science · Engineering · Mathematics · #Artificial intelligence #Benchmarking #Computer science #Control Systems and Identification #Deep learning #FOS: Computer and information sciences #Gaussian #Gaussian Processes and Bayesian Inference #Gaussian process #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine learning #Multi-task learning #Probabilistic logic #Relevance (law) #Target Tracking and Data Fusion in Sensor Networks #Task (project management) #Transfer of learning #cs.LG #stat.ML
paper · pdf · doi:10.48550/arxiv.1905.12407
published in arXiv (Cornell University) (Cornell University)
openalex publication_date 2019/05/29 · arxiv created 2020/02/23 · arxiv updated 2020/02/25 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
We present a multi-task learning formulation for Deep Gaussian processes (DGPs), through non-linear mixtures of latent processes. The latent space is composed of private processes that capture within-task information and shared processes that capture across-task dependencies. We propose two different methods for segmenting the latent space: through hard coding shared and task-specific processes or through soft sharing with Automatic Relevance Determination kernels. We show that our formulation is able to improve the learning performance and transfer information between the tasks, outperforming other probabilistic multi-task learning models across real-world and benchmarking settings.