Search Results for author: Andrea Paudice

Found 15 papers, 2 papers with code

An Improved Uniform Convergence Bound with Fat-Shattering Dimension

no code implementations13 Jul 2023 Roberto Colomboni, Emmanuel Esposito, Andrea Paudice

The fat-shattering dimension characterizes the uniform convergence property of real-valued functions.

Active Learning of Classifiers with Label and Seed Queries

no code implementations8 Sep 2022 Marco Bressan, Nicolò Cesa-Bianchi, Silvio Lattanzi, Andrea Paudice, Maximilian Thiessen

In this work we show that, by carefully combining the two types of queries, a binary classifier can be learned in time $\operatorname{poly}(n+m)$ using only $O(m^2 \log n)$ label queries and $O\big(m \log \frac{m}{\gamma}\big)$ seed queries; the result extends to $k$-class classifiers at the price of a $k! k^2$ multiplicative overhead.

Active Learning

Regret Analysis of Dyadic Search

no code implementations2 Sep 2022 François Bachoc, Tommaso Cesari, Roberto Colomboni, Andrea Paudice

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

no code implementations13 Aug 2022 François Bachoc, Tommaso Cesari, Roberto Colomboni, Andrea Paudice

This paper studies a natural generalization of the problem of minimizing a univariate convex function $f$ by querying its values sequentially.

On Margin-Based Cluster Recovery with Oracle Queries

no code implementations NeurIPS 2021 Marco Bressan, Nicolò Cesa-Bianchi, Silvio Lattanzi, Andrea Paudice

We study an active cluster recovery problem where, given a set of $n$ points and an oracle answering queries like "are these two points in the same cluster?

Multitask Online Mirror Descent

no code implementations NeurIPS 2021 Nicolò Cesa-Bianchi, Pierre Laforgue, Andrea Paudice, Massimiliano Pontil

We introduce and analyze MT-OMD, a multitask generalization of Online Mirror Descent (OMD) which operates by sharing updates between tasks.

Exact Recovery of Clusters in Finite Metric Spaces Using Oracle Queries

no code implementations31 Jan 2021 Marco Bressan, Nicolò Cesa-Bianchi, Silvio Lattanzi, Andrea Paudice

Previous results show that clusters in Euclidean spaces that are convex and separated with a margin can be reconstructed exactly using only $O(\log n)$ same-cluster queries, where $n$ is the number of input points.

Robust Unsupervised Learning via L-Statistic Minimization

no code implementations14 Dec 2020 Andreas Maurer, Daniela A. Parletta, Andrea Paudice, Massimiliano Pontil

Designing learning algorithms that are resistant to perturbations of the underlying data distribution is a problem of wide practical and theoretical importance.


Exact Recovery of Mangled Clusters with Same-Cluster Queries

no code implementations NeurIPS 2020 Marco Bressan, Nicolò Cesa-Bianchi, Silvio Lattanzi, Andrea Paudice

Given a finite set of input points, and an oracle revealing whether any two points lie in the same cluster, our goal is to recover all clusters exactly using as few queries as possible.


Correlation Clustering with Adaptive Similarity Queries

1 code implementation NeurIPS 2019 Marco Bressan, Nicolò Cesa-Bianchi, Andrea Paudice, Fabio Vitale

In this work we investigate correlation clustering as an active learning problem: each similarity score can be learned by making a query, and the goal is to minimise both the disagreements and the total number of queries.

Active Learning Clustering +1

Label Sanitization against Label Flipping Poisoning Attacks

no code implementations2 Mar 2018 Andrea Paudice, Luis Muñoz-González, Emil C. Lupu

Label flipping attacks are a special case of data poisoning, where the attacker can control the labels assigned to a fraction of the training points.

Data Poisoning

Detection of Adversarial Training Examples in Poisoning Attacks through Anomaly Detection

1 code implementation8 Feb 2018 Andrea Paudice, Luis Muñoz-González, Andras Gyorgy, Emil C. Lupu

We show empirically that the adversarial examples generated by these attack strategies are quite different from genuine points, as no detectability constrains are considered to craft the attack.

Anomaly Detection BIG-bench Machine Learning +3

Towards Poisoning of Deep Learning Algorithms with Back-gradient Optimization

no code implementations29 Aug 2017 Luis Muñoz-González, Battista Biggio, Ambra Demontis, Andrea Paudice, Vasin Wongrassamee, Emil C. Lupu, Fabio Roli

This exposes learning algorithms to the threat of data poisoning, i. e., a coordinate attack in which a fraction of the training data is controlled by the attacker and manipulated to subvert the learning process.

Data Poisoning Handwritten Digit Recognition +2

Efficient Attack Graph Analysis through Approximate Inference

no code implementations22 Jun 2016 Luis Muñoz-González, Daniele Sgandurra, Andrea Paudice, Emil C. Lupu

We compare sequential and parallel versions of Loopy Belief Propagation with exact inference techniques for both static and dynamic analysis, showing the advantages of approximate inference techniques to scale to larger attack graphs.

Bayesian Inference Clustering

Cannot find the paper you are looking for? You can Submit a new open access paper.