9 papers
Hierarchical Message-Passing Policies for Multi-Agent Reinforcement Learning
Tommaso Marzi, Cesare Alippi, Andrea Cini
Decentralized Multi-Agent Reinforcement Learning (MARL) methods allow for learning scalable multi-agent policies, but suffer from partial observability and induced non-stationarity…
Why Do Time Series Models Need Long Context Windows?
Luca Butera, Giovanni De Felice, Andrea Cini +1
Modern deep learning models for forecasting groups of time series rely on increasingly longer observation windows. However, the benefit of increasing the window size is often simpl…
Position: Current Benchmarking Hinders Real Progress in Deep Learning for Time Series Forecasting
Valentina Moretti, Ivan Marisca, Cesare Alippi +1
Deep learning models have grown popular in time series applications. However, the large quantity of newly proposed architectures and the often contradictory empirical results make…
Graph State-Space Models and Latent Relational Inference
Daniele Zambon, Andrea Cini, Cesare Alippi
State-space models effectively model multivariate time series by updating over time a representation of the system state from which predictions are made. The state representation i…
Graph Deep Learning for Time Series Forecasting
Andrea Cini, Ivan Marisca, Daniele Zambon +1
Graph deep learning methods have become popular tools to process collections of correlated time series. Unlike traditional multivariate forecasting methods, graph-based predictors…
Relational Conformal Prediction for Correlated Time Series
Andrea Cini, Alexander Jenkins, Danilo Mandic +2
We address the problem of uncertainty quantification in time series forecasting by exploiting observations at correlated sequences. Relational deep learning methods leveraging grap…