Antoine Chatalic — accepted AI-conference papers

2023

Estimating Koopman operators with sketching to provably learn large scale dynamical systems

Giacomo Meanti, Antoine Chatalic, Vladimir R Kostic, Pietro Novelli, Massimiliano Pontil, Lorenzo Rosasco

NeurIPS 2023poster

The theory of Koopman operators allows to deploy non-parametric machine learning algorithms to predict and analyze complex dynamical systems. Estimators such as principal component regression (PCR) or reduced rank regression (RRR) in kernel spaces can be shown to provably learn Koopman operators fro…

Cited by 16 Source ↗PDF ↗code ↗Scholar ↗

2023

Heteroscedastic Gaussian Processes and Random Features: Scalable Motion Primitives with Guarantees

Edoardo Caldarelli, Antoine Chatalic, Adrià Colomé, Lorenzo Rosasco, Carme Torras

CoRL 2023poster

Heteroscedastic Gaussian processes (HGPs) are kernel-based, non-parametric models that can be used to infer nonlinear functions with time-varying noise. In robotics, they can be employed for learning from demonstration as motion primitives, i.e. as a model of the trajectories to be executed by the r…

Cited by 0 Source ↗Scholar ↗

2022

Mean Nyström Embeddings for Adaptive Compressive Learning

Antoine Chatalic, Luigi Carratino, Ernesto De Vito, Lorenzo Rosasco

AISTATS 2022poster

Compressive learning is an approach to efficient large scale learning based on sketching an entire dataset to a single mean embedding (the sketch), i.e. a vector of generalized moments. The learning task is then approximately solved as an inverse problem using an adapted parametric model. Previous w…

Cited by 8 Source ↗PDF ↗code ↗Scholar ↗

2022

Nyström Kernel Mean Embeddings

Antoine Chatalic, Nicolas Schreuder, Lorenzo Rosasco, Alessandro Rudi

ICML 2022spotlight

Kernel mean embeddings are a powerful tool to represent probability distributions over arbitrary spaces as single points in a Hilbert space. Yet, the cost of computing and storing such embeddings prohibits their direct use in large-scale settings. We propose an efficient approximation procedure base…

Cited by 31 Source ↗PDF ↗code ↗Scholar ↗

2019

Differentially Private Compressive K-means

Vincent Schellekens, Antoine Chatalic, Florimond Houssiau, Yves-Alexandre de Montjoye, Laurent Jacques, Rémi Gribonval

ICASSP 2019accepted

This work addresses the problem of learning from large collections of data with privacy guarantees. The sketched learning framework proposes to deal with the large scale of datasets by compressing them into a single vector of generalized random moments, from which the learning task is then performed…

Cited by 0 Source ↗Scholar ↗

2018

Large-Scale High-Dimensional Clustering with Fast Sketching

Antoine Chatalic, Rémi Gribonval, Nicolas Keriven

ICASSP 2018accepted

In this paper, we address the problem of high-dimensional k-means clustering in a large-scale setting, i.e. for datasets that comprise a large number of items. Sketching techniques have already been used to deal with this “large-scale” issue, by compressing the whole dataset into a single vector of…

Cited by 0 Source ↗Scholar ↗