341 citations · 860 across the 36 of their papers we have counts for
40 papers
Quantifying lottery tickets under label noise: accuracy, calibration, and complexity
Viplove Arora, Daniele Irto, Sebastian Goldt +1
Pruning deep neural networks is a widely used strategy to alleviate the computational burden in machine learning. Overwhelming empirical evidence suggests that pruned models retain…
Attacks on Online Learners: a Teacher-Student Analysis
Riccardo Giuseppe Margiotta, Sebastian Goldt, Guido Sanguinetti
Machine learning models are famously vulnerable to adversarial attacks: small ad-hoc perturbations of the data that can catastrophically alter the model predictions. While a large…
Model Reduction for the Chemical Master Equation: an Information-Theoretic Approach
K. Öcal, G. Sanguinetti, R. Grima
The complexity of mathematical models in biology has rendered model reduction an essential tool in the quantitative biologist's toolkit. For stochastic reaction networks described…
On the Robustness of Bayesian Neural Networks to Adversarial Attacks
Luca Bortolussi, Ginevra Carbone, Luca Laurenti +3
Vulnerability to adversarial attacks is one of the principal hurdles to the adoption of deep learning in safety-critical applications. Despite significant efforts, both practical a…
Bayesian learning of effective chemical master equations in crowded intracellular conditions
Svitlana Braichenko, Ramon Grima, Guido Sanguinetti
Biochemical reactions inside living cells often occur in the presence of crowders -- molecules that do not participate in the reactions but influence the reaction rates through exc…
Resilience of Bayesian Layer-Wise Explanations under Adversarial Attacks
Ginevra Carbone, Guido Sanguinetti, Luca Bortolussi
We consider the problem of the stability of saliency-based explanations of Neural Network predictions under adversarial attacks in a classification task. Saliency interpretations o…
Random Projections for Improved Adversarial Robustness
Ginevra Carbone, Guido Sanguinetti, Luca Bortolussi
We propose two training techniques for improving the robustness of Neural Networks to adversarial attacks, i.e. manipulations of the inputs that are maliciously crafted to fool net…
Systematic errors in estimates of from symptomatic cases in the presence of observation bias
Guido Sanguinetti
We consider the problem of estimating the reproduction number of an epidemic for populations where the probability of detection of cases depends on a known covariate. We argu…
Estimating the impact of preventive quarantine with reverse epidemiology
Jacopo Grilli, Matteo Marsili, Guido Sanguinetti
The impact of mitigation or control measures on an epidemics can be estimated by fitting the parameters of a compartmental model to empirical data, and running the model forward wi…
Robustness of Bayesian Neural Networks to Gradient-Based Attacks
Ginevra Carbone, Matthew Wicker, Luca Laurenti +3
Vulnerability to adversarial attacks is one of the principal hurdles to the adoption of deep learning in safety-critical applications. Despite significant efforts, both practical a…
Parameter estimation for biochemical reaction networks using Wasserstein distances
Kaan Öcal, Ramon Grima, Guido Sanguinetti
We present a method for estimating parameters in stochastic models of biochemical reaction networks by fitting steady-state distributions using Wasserstein distances. We simulate a…
Geometric fluid approximation for general continuous-time Markov chains
Michalis Michaelides, Jane Hillston, Guido Sanguinetti
Fluid approximations have seen great success in approximating the macro-scale behaviour of Markov systems with a large number of discrete states. However, these methods rely on the…
Intrinsic Geometric Vulnerability of High-Dimensional Artificial Intelligence
Luca Bortolussi, Guido Sanguinetti
The success of modern Artificial Intelligence (AI) technologies depends critically on the ability to learn non-linear functional dependencies from large, high dimensional data sets…
Autoregressive Point-Processes as Latent State-Space Models: a Moment-Closure Approach to Fluctuations and Autocorrelations
M. E. Rule, G. Sanguinetti
Modeling and interpreting spike train data is a task of central importance in computational neuroscience, with significant translational implications. Two popular classes of data-d…
Gene regulatory network inference: an introductory survey
Vân Anh Huynh-Thu, Guido Sanguinetti
Gene regulatory networks are powerful abstractions of biological systems. Since the advent of high-throughput measurement technologies in biology in the late 90s, reconstructing th…
Probabilistic Model Checking for Continuous Time Markov Chains via Sequential Bayesian Inference
Dimitrios Milios, Guido Sanguinetti, David Schnoerr
Probabilistic model checking for systems with large or unbounded state space is a challenging computational problem in formal modelling and its applications. Numerical algorithms r…
Learning the structure of Bayesian Networks via the bootstrap
Giulio Caravagna, Daniele Ramazzotti
Learning the structure of dependencies among multiple random variables is a problem of considerable theoretical and practical interest. Within the context of Bayesian Networks, a p…
Efficient Low-Order Approximation of First-Passage Time Distributions
David Schnoerr, Botond Cseke, Ramon Grima +1
We consider the problem of computing first-passage time distributions for reaction processes modelled by master equations. We show that this generally intractable class of problems…
Approximation and inference methods for stochastic biochemical kinetics - a tutorial review
David Schnoerr, Guido Sanguinetti, Ramon Grima
Stochastic fluctuations of molecule numbers are ubiquitous in biological systems. Important examples include gene expression and enzymatic processes in living cells. Such systems a…
Property-driven State-Space Coarsening for Continuous Time Markov Chains
Michalis Michaelides, Dimitrios Milios, Jane Hillston +1
Dynamical systems with large state-spaces are often expensive to thoroughly explore experimentally. Coarse-graining methods aim to define simpler systems which are more amenable to…
Policy learning for time-bounded reachability in Continuous-Time Markov Decision Processes via doubly-stochastic gradient ascent
Ezio Bartocci, Luca Bortolussi, Tomǎš Brázdil +2
Continuous-time Markov decision processes are an important class of models in a wide range of applications, ranging from cyber-physical systems to synthetic biology. A central prob…
Matching models across abstraction levels with Gaussian Processes
Giulio Caravagna, Luca Bortolussi, Guido Sanguinetti
Biological systems are often modelled at different levels of abstraction depending on the particular aims/resources of a study. Such different models often provide qualitatively co…
Higher order methylation features for clustering and prediction in epigenomic studies
Chantriolnt-Andreas Kapourani, Guido Sanguinetti
Motivation: DNA methylation is an intensely studied epigenetic mark, yet its functional role is incompletely understood. Attempts to quantitatively associate average DNA methylatio…
Cox process representation and inference for stochastic reaction-diffusion processes
David Schnoerr, Ramon Grima, Guido Sanguinetti
Complex behaviour in many systems arises from the stochastic interactions of spatially distributed particles or agents. Stochastic reaction-diffusion processes are widely used to m…