70 citations · 198 across the 23 of their papers we have counts for
24 papers
Federated Wasserstein Distance
Alain Rakotomamonjy, Kimia Nadjahi, Liva Ralaivola
We introduce a principled way of computing the Wasserstein distance between two distributions in a federated manner. Namely, we show how to estimate the Wasserstein distance betwee…
Personalised Federated Learning On Heterogeneous Feature Spaces
Alain Rakotomamonjy, Maxime Vono, Hamlet Jesse Medina Ruiz +1
Most personalised federated learning (FL) approaches assume that raw data of all clients are defined in a common subspace i.e. all clients store their data according to the same sc…
Shedding a PAC-Bayesian Light on Adaptive Sliced-Wasserstein Distances
Ruben Ohana, Kimia Nadjahi, Alain Rakotomamonjy +1
The Sliced-Wasserstein distance (SW) is a computationally efficient and theoretically grounded alternative to the Wasserstein distance. Yet, the literature on its statistical prope…
Differentially Private Sliced Wasserstein Distance
Alain Rakotomamonjy, Liva Ralaivola
Developing machine learning methods that are privacy preserving is today a central topic of research, with huge practical impacts. Among the numerous ways to address privacy-preser…
Photonic Differential Privacy with Direct Feedback Alignment
Ruben Ohana, Hamlet J. Medina Ruiz, Julien Launay +4
Optical Processing Units (OPUs) -- low-power photonic chips dedicated to large scale random projections -- have been used in previous work to train deep neural networks using Direc…
Partial Trace Regression and Low-Rank Kraus Decomposition
Hachem Kadri, Stéphane Ayache, Riikka Huusari +2
The trace regression model, a direct extension of the well-studied linear regression model, allows one to map matrices to real-valued outputs. We here introduce an even more genera…
Quantum Bandits
Balthazar Casalé, Giuseppe Di Molfetta, Hachem Kadri +1
We consider the quantum version of the bandit problem known as {\em best arm identification} (BAI). We first propose a quantum modeling of the BAI problem, which assumes that both…
QuicK-means: Acceleration of K-means by learning a fast transform
Luc Giffon, Valentin Emiya, Liva Ralaivola +1
K-means -- and the celebrated Lloyd algorithm -- is more than the clustering method it was originally designed to be. It has indeed proven pivotal to help increase the speed of man…
Recovery and convergence rate of the Frank-Wolfe Algorithm for the m-EXACT-SPARSE Problem
Farah Cherfaoui, Valentin Emiya, Liva Ralaivola +1
We study the properties of the Frank-Wolfe algorithm to solve the m-EXACT-SPARSE reconstruction problem, where a signal y must be expressed as a sparse linear combination of a pred…
Frank-Wolfe Algorithm for the Exact Sparse Problem
Farah Cherfaoui, Valentin Emiya, Liva Ralaivola +1
In this paper, we study the properties of the Frank-Wolfe algorithm to solve the \ExactSparse reconstruction problem. We prove that when the dictionary is quasi-incoherent, at each…
Dependency-dependent Bounds for Sums of Dependent Random Variables
Christoph H. Lampert, Liva Ralaivola, Alexander Zimin
We consider the problem of bounding large deviations for non-i.i.d. random variables that are allowed to have arbitrary dependencies. Previous works typically assumed a specific de…
From Cutting Planes Algorithms to Compression Schemes and Active Learning
Liva Ralaivola, Ugo Louche
Cutting-plane methods are well-studied localization(and optimization) algorithms. We show that they provide a natural framework to perform machinelearning ---and not just to solve…
Greedy methods, randomization approaches and multi-arm bandit algorithms for efficient sparsity-constrained optimization
A Rakotomamonjy, S Koço, Liva Ralaivola
Several sparsity-constrained algorithms such as Orthogonal Matching Pursuit or the Frank-Wolfe algorithm with sparsity constraints work by iteratively selecting a novel atom to add…
Unconfused ultraconservative multiclass algorithms
Ugo Louche, Liva Ralaivola
We tackle the problem of learning linear classifiers from noisy datasets in a multiclass setting. The two-class version of this problem was studied a few years ago where the propos…
On Generalizing the C-Bound to the Multiclass and Multi-label Settings
Francois Laviolette, Emilie Morvant, Liva Ralaivola +1
The C-bound, introduced in Lacasse et al., gives a tight upper bound on the risk of a binary majority vote classifier. In this work, we present a first step towards extending this…
Dynamic Screening: Accelerating First-Order Algorithms for the Lasso and Group-Lasso
Antoine Bonnefoy, Valentin Emiya, Liva Ralaivola +1
Recent computational strategies based on screening tests have been proposed to accelerate algorithms addressing penalized sparse regression problems such as the Lasso. Such approac…
On the Generalization of the C-Bound to Structured Output Ensemble Methods
François Laviolette, Emilie Morvant, Liva Ralaivola +1
This paper generalizes an important result from the PAC-Bayesian literature for binary classification to the case of ensemble methods for structured outputs. We prove a generic ver…
Stationary Mixing Bandits
Julien Audiffren, Liva Ralaivola
We study the bandit problem where arms are associated with stationary phi-mixing processes and where rewards are therefore dependent: the question that arises from this setting is…
Unconfused Ultraconservative Multiclass Algorithms
Ugo Louche, Liva Ralaivola
We tackle the problem of learning linear classifiers from noisy datasets in a multiclass setting. The two-class version of this problem was studied a few years ago by, e.g. Bylande…
PAC-Bayesian Generalization Bound on Confusion Matrix for Multi-Class Classification
Emilie Morvant, Sokol Koço, Liva Ralaivola
In this work, we propose a PAC-Bayes bound for the generalization risk of the Gibbs classifier in the multi-class classification framework. The novelty of our work is the critical…
Confusion Matrix Stability Bounds for Multiclass Classification
Pierre Machart, Liva Ralaivola
In this paper, we provide new theoretical results on the generalization properties of learning algorithms for multiclass classification problems. The originality of our work is tha…
Stochastic Low-Rank Kernel Learning for Regression
Pierre Machart, Thomas Peel, Liva Ralaivola +2
We present a novel approach to learn a kernel-based regression function. It is based on the useof conical combinations of data-based parameterized kernels and on a new stochastic c…
Chromatic PAC-Bayes Bounds for Non-IID Data: Applications to Ranking and Stationary -Mixing Processes
Liva Ralaivola, Marie Szafranski, Guillaume Stempfel
Pac-Bayes bounds are among the most accurate generalization bounds for classifiers learned from independently and identically distributed (IID) data, and it is particularly so for…
The pharmacophore kernel for virtual screening with support vector machines
Pierre Mahé, Liva Ralaivola, Véronique Stoven +1
We introduce a family of positive definite kernels specifically optimized for the manipulation of 3D structures of molecules with kernel methods. The kernels are based on the compa…