6 papers
Central limit theorems for the outputs of fully convolutional neural networks with time series input
Annika Betken, Giorgio Micali, Johannes Schmidt-Hieber
Deep learning is widely deployed for time series learning tasks such as classification and forecasting. Despite the empirical successes, only little theory has been developed so fa…
Ordinal Patterns Based Testing of Spatial Independence in Irregular Spatial Structures
Giorgio Micali, David Garnés-Galindo, Mariano Matilla-GarcÃa +1
We propose a nonparametric test of spatial independence for data observed on irregular, non-lattice point clouds . For each location $v\in\mat…
Symmetry Testing in Time Series using Ordinal Patterns: A U-Statistic Approach
Annika Betken, Giorgio Micali, Manuel Ruiz MarÃn
We introduce a general framework for testing temporal symmetries in time series based on the distribution of ordinal patterns. While previous approaches have focused on specific fo…
Secure Change-Point Detection for Time Series under Homomorphic Encryption
Federico Mazzone, Giorgio Micali, Massimiliano Pronesti
We introduce the first method for change-point detection on encrypted time series. Our approach employs the CKKS homomorphic encryption scheme to detect shifts in statistical prope…
Ordinal Patterns Based Change Points Detection
Annika Betken, Giorgio Micali, Johannes Schmidt-Hieber
The ordinal patterns of a fixed number of consecutive values in a time series is the spatial ordering of these values. Counting how often a specific ordinal pattern occurs in a tim…
Differentially Private Algorithms for Linear Queries via Stochastic Convex Optimization
Giorgio Micali, Clement Lezane, Annika Betken
This article establishes a method to answer a finite set of linear queries on a given dataset while ensuring differential privacy. To achieve this, we formulate the corresponding t…