114 citations · 132 across the 12 of their papers we have counts for
15 papers
An Improved Uniform Convergence Bound with Fat-Shattering Dimension
Roberto Colomboni, Emmanuel Esposito, Andrea Paudice
The fat-shattering dimension characterizes the uniform convergence property of real-valued functions. The state-of-the-art upper bounds feature a multiplicative squared logarithmic…
Regret Analysis of Dyadic Search
François Bachoc, Tommaso Cesari, Roberto Colomboni +1
We analyze the cumulative regret of the Dyadic Search algorithm of Bachoc et al. [2022].
A Near-Optimal Algorithm for Univariate Zeroth-Order Budget Convex Optimization
François Bachoc, Tommaso Cesari, Roberto Colomboni +1
This paper studies a natural generalization of the problem of minimizing a univariate convex function by querying its values sequentially. At each time-step , the optimizer…
Active Learning of Classifiers with Label and Seed Queries
Marco Bressan, Nicolò Cesa-Bianchi, Silvio Lattanzi +2
We study exact active learning of binary and multiclass classifiers with margin. Given an -point set , we want to learn any unknown classifier on who…
High Probability Bounds for Stochastic Subgradient Schemes with Heavy Tailed Noise
Daniela A. Parletta, Andrea Paudice, Massimiliano Pontil +1
In this work we study high probability bounds for stochastic subgradient methods under heavy tailed noise. In this setting the noise is only assumed to have finite variance as oppo…
On Margin-Based Cluster Recovery with Oracle Queries
Marco Bressan, Nicolò Cesa-Bianchi, Silvio Lattanzi +1
We study an active cluster recovery problem where, given a set of points and an oracle answering queries like "are these two points in the same cluster?", the task is to recove…
Multitask Online Mirror Descent
Nicolò Cesa-Bianchi, Pierre Laforgue, Andrea Paudice +1
We introduce and analyze MT-OMD, a multitask generalization of Online Mirror Descent (OMD) which operates by sharing updates between tasks. We prove that the regret of MT-OMD is of…
Exact Recovery of Clusters in Finite Metric Spaces Using Oracle Queries
Marco Bressan, Nicolò Cesa-Bianchi, Silvio Lattanzi +1
We investigate the problem of exact cluster recovery using oracle queries. Previous results show that clusters in Euclidean spaces that are convex and separated with a margin can b…
Robust Unsupervised Learning via L-Statistic Minimization
Andreas Maurer, Daniela A. Parletta, Andrea Paudice +1
Designing learning algorithms that are resistant to perturbations of the underlying data distribution is a problem of wide practical and theoretical importance. We present a genera…
Exact Recovery of Mangled Clusters with Same-Cluster Queries
Marco Bressan, Nicolò Cesa-Bianchi, Silvio Lattanzi +1
We study the cluster recovery problem in the semi-supervised active clustering framework. Given a finite set of input points, and an oracle revealing whether any two points lie in…
Correlation Clustering with Adaptive Similarity Queries
Marco Bressan, Nicolò Cesa-Bianchi, Andrea Paudice +1
In correlation clustering, we are given objects together with a binary similarity score between each pair of them. The goal is to partition the objects into clusters so to mini…
Label Sanitization against Label Flipping Poisoning Attacks
Andrea Paudice, Luis Muñoz-González, Emil C. Lupu
Many machine learning systems rely on data collected in the wild from untrusted sources, exposing the learning algorithms to data poisoning. Attackers can inject malicious data in…
Detection of Adversarial Training Examples in Poisoning Attacks through Anomaly Detection
Andrea Paudice, Luis Muñoz-González, Andras Gyorgy +1
Machine learning has become an important component for many systems and applications including computer vision, spam filtering, malware and network intrusion detection, among other…
Towards Poisoning of Deep Learning Algorithms with Back-gradient Optimization
Luis Muñoz-González, Battista Biggio, Ambra Demontis +4
A number of online services nowadays rely upon machine learning to extract valuable information from data collected in the wild. This exposes learning algorithms to the threat of d…
Efficient Attack Graph Analysis through Approximate Inference
Luis Muñoz-González, Daniele Sgandurra, Andrea Paudice +1
Attack graphs provide compact representations of the attack paths that an attacker can follow to compromise network resources by analysing network vulnerabilities and topology. The…