no code implementations • COLING (CRAC) 2020 • Onkar Pandit, Pascal Denis, Liva Ralaivola
Specifically, we convert the external knowledge source (in this case, WordNet) into a graph, and learn embeddings of the graph nodes of low dimension to capture the crucial features of the graph topology and, at the same time, rich semantic information.
no code implementations • 3 Oct 2023 • Alain Rakotomamonjy, Kimia Nadjahi, Liva Ralaivola
We introduce a principled way of computing the Wasserstein distance between two distributions in a federated manner.
no code implementations • 26 Jan 2023 • Alain Rakotomamonjy, Maxime Vono, Hamlet Jesse Medina Ruiz, Liva Ralaivola
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 schema.
1 code implementation • 7 Jun 2022 • Ruben Ohana, Kimia Nadjahi, Alain Rakotomamonjy, Liva Ralaivola
The Sliced-Wasserstein distance (SW) is a computationally efficient and theoretically grounded alternative to the Wasserstein distance.
1 code implementation • 5 Jul 2021 • Alain Rakotomamonjy, Liva Ralaivola
Developing machine learning methods that are privacy preserving is today a central topic of research, with huge practical impacts.
no code implementations • NeurIPS 2021 • Ruben Ohana, Hamlet J. Medina Ruiz, Julien Launay, Alessandro Cappelli, Iacopo Poli, Liva Ralaivola, Alain Rakotomamonjy
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 Direct Feedback Alignment (DFA), an effective alternative to backpropagation.
1 code implementation • ICML 2020 • Hachem Kadri, Stéphane Ayache, Riikka Huusari, Alain Rakotomamonjy, Liva Ralaivola
The trace regression model, a direct extension of the well-studied linear regression model, allows one to map matrices to real-valued outputs.
no code implementations • 15 Feb 2020 • Balthazar Casalé, Giuseppe Di Molfetta, Hachem Kadri, Liva Ralaivola
We consider the quantum version of the bandit problem known as {\em best arm identification} (BAI).
no code implementations • 23 Aug 2019 • Luc Giffon, Valentin Emiya, Liva Ralaivola, Hachem Kadri
K-means -- and the celebrated Lloyd algorithm -- is more than the clustering method it was originally designed to be.
no code implementations • 18 Dec 2018 • Farah Cherfaoui, Valentin Emiya, Liva Ralaivola, Sandrine Anthoine
In this paper, we study the properties of the Frank-Wolfe algorithm to solve the \ExactSparse reconstruction problem.
no code implementations • NeurIPS 2017 • Julien Audiffren, Liva Ralaivola
We propose an algorithm, UnchainedBandits, that efficiently finds the set of optimal arms, or Pareto front, of any poset even when pairs of comparable arms cannot be a priori distinguished from pairs of incomparable arms, with a set of minimal assumptions.
no code implementations • EACL 2017 • Pascal Denis, Liva Ralaivola
This paper presents a new, efficient method for learning task-specific word vectors using a variant of the Passive-Aggressive algorithm.
no code implementations • NeurIPS 2015 • Julien Audiffren, Liva Ralaivola
We study the restless bandit problem where arms are associated with stationary $\varphi$-mixing processes and where rewards are therefore dependent: the question that arises from this setting is that of carefully recovering some independence by `ignoring' the values of some rewards.
no code implementations • 26 Aug 2015 • 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 to the current non-zero set of variables.
no code implementations • 12 Aug 2015 • Liva Ralaivola, Ugo Louche
Cutting-plane methods are well-studied localization(and optimization) algorithms.
no code implementations • 24 Jun 2015 • Ugo Louche, Liva Ralaivola
We tackle the problem of learning linear classifiers from noisy datasets in a multiclass setting.
no code implementations • 13 Jan 2015 • Francois Laviolette, Emilie Morvant, Liva Ralaivola, Jean-Francis Roy
The C-bound, introduced in Lacasse et al., gives a tight upper bound on the risk of a binary majority vote classifier.
no code implementations • 12 Dec 2014 • Antoine Bonnefoy, Valentin Emiya, Liva Ralaivola, Rémi Gribonval
Recent computational strategies based on screening tests have been proposed to accelerate algorithms addressing penalized sparse regression problems such as the Lasso.
no code implementations • 6 Aug 2014 • François Laviolette, Emilie Morvant, Liva Ralaivola, Jean-Francis Roy
This paper generalizes an important result from the PAC-Bayesian literature for binary classification to the case of ensemble methods for structured outputs.
no code implementations • 23 Jun 2014 • Julien Audiffren, Liva Ralaivola
To do so, we provide a UCB strategy together with a general regret analysis for the case where the size of the independence blocks (the ignored rewards) is fixed and we go a step beyond by providing an algorithm that is able to compute the size of the independence blocks from the data.
no code implementations • 20 Mar 2014 • Ugo Louche, Liva Ralaivola
We tackle the problem of learning linear classifiers from noisy datasets in a multiclass setting.
no code implementations • NeurIPS 2012 • Liva Ralaivola
This paper provides the first ---to the best of our knowledge--- analysis of online learning algorithms for multiclass problems when the {\em confusion} matrix is taken as a performance measure.
no code implementations • 28 Feb 2012 • 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.
no code implementations • NeurIPS 2010 • Thomas Peel, Sandrine Anthoine, Liva Ralaivola
They are expressed with respect to empirical estimates of either the variance of q or the conditional variance that appears in the Bernstein-type inequality for U-statistics derived by Arcones [2].