Publications (24)
Predicate Logic as a Modeling Language: Modeling and Solving some Machine Learning and Data Mining Problems with IDP3
Maurice Bruynooghe, Hendrik Blockeel, Bart Bogaerts +7
This paper provides a gentle introduction to problem solving with the IDP3 system. The core of IDP3 is a finite model generator that supports first order logic enriched with types,…
Constrained Multi-Relational Graphons with Maximum Entropy
Juan Alvarado, Jan Ramon, Yuyi Wang
The principle of maximum entropy provides a fundamental framework for characterizing typical structures of large random networks subject to observable constraints. In their pioneer…
Accurate, private, secure, federated U-statistics with higher degree
Quentin Sinh, Jan Ramon
We study the problem of computing a U-statistic with a kernel function f of degree k 2, i.e., the average of some function f over all k-tuples of instances, in a federated le…
Secure Sparse Matrix Multiplications and their Applications to Privacy-Preserving Machine Learning
Marc Damie, Florian Hahn, Andreas Peter +1
To preserve data privacy, multi-party computation (MPC) enables executing Machine Learning (ML) algorithms on private data. However, MPC frameworks do not include optimized operati…
Learning from networked examples in a k-partite graph
Yuyi Wang, Jan Ramon, Zheng-Chu Guo
Many machine learning algorithms are based on the assumption that training examples are drawn independently. However, this assumption does not hold anymore when learning from a net…
How to Securely Shuffle? A survey about Secure Shufflers for privacy-preserving computations
Marc Damie, Florian Hahn, Andreas Peter +1
Ishai et al. (FOCS'06) introduced secure shuffling as an efficient building block for private data aggregation. Recently, the field of differential privacy has revived interest in…
Gradient Projection onto Historical Descent Directions for Communication-Efficient Federated Learning
Arnaud Descours, Léonard Deroose, Jan Ramon
Federated Learning (FL) enables decentralized model training across multiple clients while optionally preserving data privacy. However, communication efficiency remains a critical…
A lower bound on the probability that a binomial random variable is exceeding its mean
Christos Pelekis, Jan Ramon
We provide a lower bound on the probability that a binomial random variable is exceeding its mean. Our proof employs estimates on the mean absolute deviation and the tail condition…
Eliminating Exponential Key Growth in PRG-Based Distributed Point Functions
Marc Damie, Florian Hahn, Andreas Peter +1
Distributed Point Functions (DPFs) enable sharing secret point functions across multiple parties, supporting privacy-preserving technologies such as Private Information Retrieval,…
Solving linear programs on factorized databases
Florent Capelli, Nicolas Crosetti, Joachim Niehren +1
A typical workflow for solving a linear programming problem is to first write a linear program parametrized by the data in a language such as Math GNU Prog or AMPL then call the so…
Learning from networked examples
Yuyi Wang, Jan Ramon, Zheng-Chu Guo
Many machine learning algorithms are based on the assumption that training examples are drawn independently. However, this assumption does not hold anymore when learning from a net…
Dropout-Robust Mechanisms for Differentially Private and Fully Decentralized Mean Estimation
César Sabater, Sonia Ben Mokhtar, Jan Ramon
Achieving differentially private computations in decentralized settings poses significant challenges, particularly regarding accuracy, communication cost, and robustness against in…
Differentially Private Empirical Cumulative Distribution Functions
Antoine Barczewski, Amal Mawass, Jan Ramon
In order to both learn and protect sensitive training data, there has been a growing interest in privacy preserving machine learning methods. Differential privacy has emerged as an…
Hiding in the Crowd: A Massively Distributed Algorithm for Private Averaging with Malicious Adversaries
Pierre Dellenbach, Aurélien Bellet, Jan Ramon
The amount of personal data collected in our everyday interactions with connected devices offers great opportunities for innovative services fueled by machine learning, as well as…
Linear Programs with Conjunctive Database Queries
Florent Capelli, Nicolas Crosetti, Joachim Niehren +1
In this paper, we study the problem of optimizing a linear program whose variables are the answers to a conjunctive query. For this we propose the language LP(CQ) for specifying li…
An Accurate, Scalable and Verifiable Protocol for Federated Differentially Private Averaging
César Sabater, Aurélien Bellet, Jan Ramon
Learning from data owned by several parties, as in federated learning, raises challenges regarding the privacy guarantees provided to participants and the correctness of the comput…
Hölder-type inequalities and their applications to concentration and correlation bounds
Christos Pelekis, Jan Ramon, Yuyi Wang
Let be -valued random variables having a dependency graph . We show that \[ \mathbb{E}\left[\prod_{v\in V} Y_{v} \right] \leq \prod_{v\in V} \left\{…
Top-down induction of clustering trees
Hendrik Blockeel, Luc De Raedt, Jan Ramon
An approach to clustering is presented that adapts the basic top-down induction of decision trees method towards clustering. To this aim, it employs the principles of instance base…
DDH-based schemes for multi-party Function Secret Sharing
Marc Damie, Florian Hahn, Andreas Peter +1
Function Secret Sharing (FSS) schemes enable sharing efficiently secret functions. Schemes dedicated to point functions, referred to as Distributed Point Functions (DPFs), are the…
On the Bernstein-Hoeffding method
Christos Pelekis, Jan Ramon, Yuyi Wang
We show that the Bernstein-Hoeffding method can be employed to a larger class of generalized moments. This class includes the exponential moments whose properties play a key role i…
Constrained Multi-Relational Hyper-Graphons with Maximum Entropy
Juan Alvarado, Jan Ramon, Yuyi Wang
This work has two contributions. The first one is extending the Large Deviation Principle for uniform hyper-graphons from Lubetzky and Zhao \cite{lubetzky2015replica} to the multi-…
Hoeffding's inequality for sums of weakly dependent random variables
Christos Pelekis, Jan Ramon
We provide a systematic approach to deal with the following problem. Let be, possibly dependent, -valued random variables. What is a sharp upper bound on th…
DP-SGD with weight clipping
Antoine Barczewski, Jan Ramon
Recently, due to the popularity of deep neural networks and other methods whose training typically relies on the optimization of an objective function, and due to concerns for data…
SoK: Verifiable Cross-Silo FL
Aleksei Korneev, Jan Ramon
Federated Learning (FL) is a widespread approach that allows training machine learning (ML) models with data distributed across multiple devices. In cross-silo FL, which often appe…