10 citations · 26 across the 17 of their papers we have counts for
20 papers
Poisson empirical Bayes estimation of sums of random variables via minimum-distance methods
Stefano Favaro, Sandra Fortini, Soham Jana
The estimation of sums of functions of observable and unobservable variables is a long-standing problem in statistics, with applications in many domains. We consider this problem i…
Merging of Bayes and quasi-Bayes empirical Bayes procedures for Poisson compound decisions
Stefano Favaro, Sandra Fortini
The Poisson compound decision problem is a long-standing problem in statistics, in which empirical Bayes methods are used to estimate Poisson means under a mixture model. We study…
Quasi-Bayes empirical Bayes estimation of sums of random variables
Stefano Favaro, Sandra Fortini
The estimation of sums of functions of observable and unobservable variables is a long-standing problem in statistics with applications across many domains. Empirical Bayes methods…
Uncertainty Decomposition for Bayes-Filtered Transformers via Bayesian Predictive Inference
Sandra Fortini, Kenyon Ng, Sonia Petrone +2
Bayes-filtered transformers are transformers meta-learned on sequences from a prior predictive distribution to approximate the corresponding posterior predictive distribution. They…
Quasi-Bayes empirical Bayes: a sequential approach to the Poisson compound decision problem
Stefano Favaro, Sandra Fortini
The Poisson compound decision problem is a long-standing problem is statistics, for which empirical Bayes methods are commonly used to estimate Poisson means in static or batch set…
Quasi-Bayesian sequential deconvolution
Stefano Favaro, Sandra Fortini
Density deconvolution is the inverse problem of estimating a probability density from observations contaminated by additive noise. Traditionally studied in static or batch settings…
Exchangeability, prediction and predictive modeling in Bayesian statistics
Sandra Fortini, Sonia Petrone
There is currently a renewed interest in the Bayesian predictive approach to statistics. This paper offers a review on foundational concepts and focuses on predictive modeling, whi…
Infinitely wide limits for deep Stable neural networks: sub-linear, linear and super-linear activation functions
Alberto Bordino, Stefano Favaro, Sandra Fortini
There is a growing literature on the study of large-width properties of deep Gaussian neural networks (NNs), i.e. deep NNs with Gaussian-distributed parameters or weights, and Gaus…
Non-asymptotic approximations of Gaussian neural networks via second-order Poincaré inequalities
Alberto Bordino, Stefano Favaro, Sandra Fortini
There is a recent and growing literature on large-width asymptotic and non-asymptotic properties of deep Gaussian neural networks (NNs), namely NNs with weights initialized as Gaus…
Large-width asymptotics for ReLU neural networks with -Stable initializations
Stefano Favaro, Sandra Fortini, Stefano Peluchetti
There is a recent and growing literature on large-width asymptotic properties of Gaussian neural networks (NNs), namely NNs whose weights are initialized as Gaussian distributions.…
Deep Stable neural networks: large-width asymptotics and convergence rates
Stefano Favaro, Sandra Fortini, Stefano Peluchetti
In modern deep learning, there is a recent and growing literature on the interplay between large-width asymptotic properties of deep Gaussian neural networks (NNs), i.e. deep NNs w…
Infinite-color randomly reinforced urns with dominant colors
Hristo Sariev, Sandra Fortini, Sonia Petrone
We define and prove limit results for a class of dominant Pólya sequences, which are randomly reinforced urn processes with color-specific random weights and unbounded number of po…
Approximating the Operating Characteristics of Bayesian Uncertainty Directed Trial Designs
Marta Bonsaglio, Sandra Fortini, Steffen Ventz +1
Bayesian response adaptive clinical trials are currently evaluating experimental therapies for several diseases. Adaptive decisions, such as pre-planned variations of the randomiza…
Large-width functional asymptotics for deep Gaussian neural networks
Daniele Bracale, Stefano Favaro, Sandra Fortini +1
In this paper, we consider fully connected feed-forward deep neural networks where weights and biases are independent and identically distributed according to Gaussian distribution…
Infinite-channel deep stable convolutional neural networks
Daniele Bracale, Stefano Favaro, Sandra Fortini +1
The interplay between infinite-width neural networks (NNs) and classes of Gaussian processes (GPs) is well known since the seminal work of Neal (1996). While numerous theoretical r…
Stable behaviour of infinitely wide deep neural networks
Stefano Favaro, Sandra Fortini, Stefano Peluchetti
We consider fully connected feed-forward deep neural networks (NNs) where weights and biases are independent and identically distributed as symmetric centered stable distributions.…
Quasi-Bayes properties of a recursive procedure for mixtures
Sandra Fortini, Sonia Petrone
Bayesian methods are often optimal, yet increasing pressure for fast computations, especially with streaming data, brings renewed interest in faster, possibly sub-optimal, solution…
On a notion of partially conditionally identically distributed sequences
Sandra Fortini, Sonia Petrone, Polina Sporysheva
A notion of conditionally identically distributed (c.i.d.) sequences has been studied as a form of stochastic dependence that is weaker than exchangeability, but is equivalent to e…
Predictive Characterization of Mixtures of Markov Chains
Sandra Fortini, Sonia Petrone
Predictive constructions are a powerful way of characterizing the probability law of stochastic processes with certain forms of invariance, such as exchangeability or Markov exchan…
Central Limit Theorem with Exchangeable Summands and Mixtures of Stable Laws as Limits
Sandra Fortini, Lucia Ladelli, Eugenio Regazzini
The problem of convergence in law of normed sums of exchangeable random variables is examined. First, the problem is studied w.r.t. arrays of exchangeable random variables, and the…