Searcharxiv⌕ Search

arXiv subjects

Riccardo Lazzarini

Publications and source records attributed to Riccardo Lazzarini.

2 recordsLinked to original sources

Robust Gaussian process regression: posterior contraction

Gaussian processes form a popular and flexible class of prior distributions with principled uncertainty quantification, but the Gaussian likelihood on which the corresponding posterior relies makes them highly sensitive to outliers and contaminated observations. We study Gaussian process regression when among the $n$ observations, $m$ of these are possibly contaminated. A generic framework to obtain posterior contraction rates in this setting is considered, from a frequentist perspective as the sample size $n$ and the number of corrupted observations $m$ grow. We adopt a generalized Bayes approach in which the log--likelihood is replaced by a robustified version; we discuss various choices thereof, such as one recently proposed by Altamirano et al. that preserves conjugacy. We investigate the minimax rate of estimation under adversarial contamination in terms of the Sobolev smoothness $β$ of the regression function and $m$. The question of building adaptive procedures to both $β$ and $m$ is investigated, and we show that a polynomial loss for adaptation must be paid in general. We instantiate our results for Matérn Gaussian process and deep ReLU network priors. Numerical experiments for existing and new robust algorithms are provided, illustrating the practical applicability of our results.

math.ST↗

Bayesian Nonparametric Privacy-Preserving Synthetic Data Generation: I. Discrete Data

Synthetic data generation is a powerful approach to privacy-preserving statistical analysis, where data-release mechanisms are governed by a privacy-utility tradeoff: they should provide privacy guarantees while preserving the statistical utility of confidential data. We develop a Bayesian nonparametric framework for private synthetic data generation tailored to discrete data. Specifically, the confidential data are modeled as a random sample from an unknown discrete distribution endowed with a Pitman-Yor process prior, and synthetic data are generated from the corresponding posterior-predictive distribution. Since the Pitman-Yor process defines an almost surely discrete random probability measure, the resulting mechanism is naturally suited to data with ties and settings involving a potentially large, unknown, or growing number of categories. We study differential privacy guarantees of the Pitman-Yor posterior-predictive mechanism across the three regimes of the discount parameter $σ\in(-\infty,1)$. For $σ\in(0,1)$, we establish an instance-level $(\varepsilon,δ)$-differential privacy guarantee. For $σ=0$ and $σ<0$, corresponding respectively to the Dirichlet process prior and to a parametric Dirichlet-Multinomial model, stronger guarantees are obtained, under suitable conditions on the released sample size. We also investigate statistical utility, or informativity, of the released data via the expected $1$-Wasserstein distance between the empirical distribution of the synthetic data and the "true" data-generating distribution. For $σ<0$ and $σ=0$, we prove consistency of the empirical distribution in this metric and derive explicit convergence rates, making precise the privacy-utility tradeoff: stronger privacy guarantees impose more restrictive choices of the released sample size, slowing down convergence to the "true" data-generating distribution.

math.ST↗