5 papers
DeGAS: Gradient-Based Optimization of Probabilistic Programs without Sampling
Francesca Randone, Romina Doz, Mirco Tribastone +1
We present DeGAS, a differentiable Gaussian approximate semantics for loopless probabilistic programs that enables sample-free, gradient-based optimization in models with both cont…
Conformal Predictive Monitoring for Multi-Modal Scenarios
Francesca Cairoli, Luca Bortolussi, Jyotirmoy V. Deshmukh +2
We consider the problem of quantitative predictive monitoring (QPM) of stochastic systems, i.e., predicting at runtime the degree of satisfaction of a desired temporal logic proper…
CoCAI: Copula-based Conformal Anomaly Identification for Multivariate Time-Series
Nicholas A. Pearson, Francesca Zanello, Davide Russo +2
We propose a novel framework that harnesses the power of generative artificial intelligence and copula-based modeling to address two critical challenges in multivariate time-series…
Diffusion-based Time Series Forecasting for Sewerage Systems
Nicholas A. Pearson, Francesca Cairoli, Luca Bortolussi +2
We introduce a novel deep learning approach that harnesses the power of generative artificial intelligence to enhance the accuracy of contextual forecasting in sewerage systems. By…
ResiDual Transformer Alignment with Spectral Decomposition
Lorenzo Basile, Valentino Maiorca, Luca Bortolussi +2
When examined through the lens of their residual streams, a puzzling property emerges in transformer networks: residual contributions (e.g., attention heads) sometimes specialize i…