142 citations · 600 across the 47 of their papers we have counts for
48 papers
One-Line-of-Code Data Mollification Improves Optimization of Likelihood-based Generative Models
Ba-Hien Tran, Giulio Franzese, Pietro Michiardi +1
Generative Models (GMs) have attracted considerable attention due to their tremendous success in various domains, such as computer vision where they are capable to generate impress…
When is Importance Weighting Correction Needed for Covariate Shift Adaptation?
Davit Gogolashvili, Matteo Zecchin, Motonobu Kanagawa +2
This paper investigates when the importance weighting (IW) correction is needed to address covariate shift, a common situation in supervised learning where the input distributions…
Continuous-Time Functional Diffusion Processes
Giulio Franzese, Giulio Corallo, Simone Rossi +3
We introduce Functional Diffusion Processes (FDPs), which generalize score-based diffusion models to infinite-dimensional function spaces. FDPs require a new mathematical framework…
Fully Bayesian Autoencoders with Latent Sparse Gaussian Processes
Ba-Hien Tran, Babak Shahbaba, Stephan Mandt +1
Autoencoders and their variants are among the most widely used models in representation learning and generative modeling. However, autoencoder-based models usually assume that the…
Locally Smoothed Gaussian Process Regression
Davit Gogolashvili, Bogdan Kozyrskiy, Maurizio Filippone
We develop a novel framework to accelerate Gaussian process regression (GPR). In particular, we consider localization kernels at each data point to down-weigh the contributions fro…
How Much is Enough? A Study on Diffusion Times in Score-based Generative Models
Giulio Franzese, Simone Rossi, Lixuan Yang +4
Score-based diffusion models are a class of generative models whose dynamics is described by stochastic differential equations that map noise into data. While recent works have sta…
Local Random Feature Approximations of the Gaussian Kernel
Jonas Wacker, Maurizio Filippone
A fundamental drawback of kernel-based statistical models is their limited scalability to large data sets, which requires resorting to approximations. In this work, we focus on the…
Complex-to-Real Sketches for Tensor Products with Applications to the Polynomial Kernel
Jonas Wacker, Ruben Ohana, Maurizio Filippone
Randomized sketches of a tensor product of vectors follow a tradeoff between statistical efficiency and computational acceleration. Commonly used approaches avoid computing the…
Improved Random Features for Dot Product Kernels
Jonas Wacker, Motonobu Kanagawa, Maurizio Filippone
Dot product kernels, such as polynomial and exponential (softmax) kernels, are among the most widely used kernels in machine learning, as they enable modeling the interactions betw…
Model Selection for Bayesian Autoencoders
Ba-Hien Tran, Simone Rossi, Dimitrios Milios +3
We develop a novel method for carrying out model selection for Bayesian autoencoders (BAEs) by means of prior hyper-parameter optimization. Inspired by the common practice of type-…
Revisiting the Effects of Stochasticity for Hamiltonian Samplers
Giulio Franzese, Dimitrios Milios, Maurizio Filippone +1
We revisit the theoretical properties of Hamiltonian stochastic differential equations (SDES) for Bayesian posterior sampling, and we study the two types of errors that arise from…
All You Need is a Good Functional Prior for Bayesian Deep Learning
Ba-Hien Tran, Simone Rossi, Dimitrios Milios +1
The Bayesian treatment of neural networks dictates that a prior distribution is specified over their weight and bias parameters. This poses a challenge because modern neural networ…
Sparse within Sparse Gaussian Processes using Neighbor Information
Gia-Lac Tran, Dimitrios Milios, Pietro Michiardi +1
Approximations to Gaussian processes based on inducing variables, combined with variational inference techniques, enable state-of-the-art sparse approaches to infer GPs at scale th…
An Identifiable Double VAE For Disentangled Representations
Graziano Mita, Maurizio Filippone, Pietro Michiardi
A large part of the literature on learning disentangled representations focuses on variational autoencoders (VAE). Recent developments demonstrate that disentanglement cannot be ob…
Isotropic SGD: a Practical Approach to Bayesian Posterior Sampling
Giulio Franzese, Rosa Candela, Dimitrios Milios +2
In this work we define a unified mathematical framework to deepen our understanding of the role of stochastic gradient (SG) noise on the behavior of Markov chain Monte Carlo sampli…
A Variational View on Bootstrap Ensembles as Bayesian Inference
Dimitrios Milios, Pietro Michiardi, Maurizio Filippone
In this paper, we employ variational arguments to establish a connection between ensemble methods for Neural Networks and Bayesian inference. We consider an ensemble-based scheme w…
Model Monitoring and Dynamic Model Selection in Travel Time-series Forecasting
Rosa Candela, Pietro Michiardi, Maurizio Filippone +1
Accurate travel products price forecasting is a highly desired feature that allows customers to take informed decisions about purchases, and companies to build and offer attractive…
Sparse Gaussian Processes Revisited: Bayesian Approaches to Inducing-Variable Approximations
Simone Rossi, Markus Heinonen, Edwin V. Bonilla +2
Variational inference techniques based on inducing variables provide an elegant framework for scalable posterior estimation in Gaussian process (GP) models. Besides enabling scalab…
Kernel computations from large-scale random features obtained by Optical Processing Units
Ruben Ohana, Jonas Wacker, Jonathan Dong +4
Approximating kernel functions with random features (RFs)has been a successful application of random projections for nonparametric estimation. However, performing random projection…
Efficient Approximate Inference with Walsh-Hadamard Variational Inference
Simone Rossi, Sebastien Marmin, Maurizio Filippone
Variational inference offers scalable and flexible tools to tackle intractable Bayesian inference of modern statistical models like Bayesian neural networks and Gaussian processes.…
LIBRE: Learning Interpretable Boolean Rule Ensembles
Graziano Mita, Paolo Papotti, Maurizio Filippone +1
We present a novel method - LIBRE - to learn an interpretable classifier, which materializes as a set of Boolean rules. LIBRE uses an ensemble of bottom-up weak learners operating…
Sparsification as a Remedy for Staleness in Distributed Asynchronous SGD
Rosa Candela, Giulio Franzese, Maurizio Filippone +1
Large scale machine learning is increasingly relying on distributed optimization, whereby several machines contribute to the training process of a statistical model. In this work w…
Deep Compositional Spatial Models
Andrew Zammit-Mangion, Tin Lok James Ng, Quan Vu +1
Spatial processes with nonstationary and anisotropic covariance structure are often used when modelling, analysing and predicting complex environmental phenomena. Such processes ma…
Walsh-Hadamard Variational Inference for Bayesian Deep Learning
Simone Rossi, Sebastien Marmin, Maurizio Filippone
Over-parameterized models, such as DeepNets and ConvNets, form a class of models that are routinely adopted in a wide variety of applications, and for which Bayesian inference is d…