no code implementations • 19 Feb 2024 • Paul Krzakala, Junjie Yang, Rémi Flamary, Florence d'Alché-Buc, Charlotte Laclau, Matthieu Labeau
We present a novel end-to-end deep learning-based approach for Supervised Graph Prediction (SGP).
no code implementations • 26 Dec 2023 • Romain Valla, Pavlo Mozharovskyi, Florence d'Alché-Buc
At the crossway of machine learning and data analysis, anomaly detection aims at identifying observations that exhibit abnormal behaviour.
no code implementations • 21 Dec 2023 • Arturo Castellanos, Pavlo Mozharovskyi, Florence d'Alché-Buc, Hicham Janati
Data depth is a statistical function that generalizes order and quantiles to the multivariate setting and beyond, with applications spanning over descriptive and visual statistics, anomaly detection, testing, etc.
1 code implementation • 2 Nov 2023 • Quentin Bouniot, Pavlo Mozharovskyi, Florence d'Alché-Buc
Data augmentation is an essential building block for learning efficient deep learning models.
no code implementations • 28 Sep 2023 • Junjie Yang, Matthieu Labeau, Florence d'Alché-Buc
Pairwise comparison of graphs is key to many applications in Machine learning ranging from clustering, kernel-based classification/regression and more recently supervised graph prediction.
no code implementations • 11 May 2023 • Jayneel Parekh, Sanjeel Parekh, Pavlo Mozharovskyi, Gaël Richard, Florence d'Alché-Buc
This paper tackles two major problem settings for interpretability of audio processing networks, post-hoc and by-design interpretation.
no code implementations • 20 Feb 2023 • Tamim El Ahmad, Luc Brogat-Motte, Pierre Laforgue, Florence d'Alché-Buc
Surrogate kernel-based methods offer a flexible solution to structured output prediction by leveraging the kernel trick in both input and output spaces.
no code implementations • 16 Nov 2022 • Luc Brogat-Motte, Alessandro Rudi, Céline Brouard, Juho Rousu, Florence d'Alché-Buc
We propose and analyse a reduced-rank method for solving least-squares regression problems with infinite dimensional output.
1 code implementation • 16 Jun 2022 • Alex Lambert, Dimitri Bouche, Zoltan Szabo, Florence d'Alché-Buc
The efficiency of the approach is demonstrated and contrasted with the classical squared loss setting on both synthetic and real-world benchmarks.
1 code implementation • 8 Jun 2022 • Tamim El Ahmad, Pierre Laforgue, Florence d'Alché-Buc
Kernel methods are learning algorithms that enjoy solid theoretical foundations while suffering from important computational limitations.
no code implementations • 20 Apr 2022 • Dimitri Bouche, Rémi Flamary, Florence d'Alché-Buc, Riwal Plougonven, Marianne Clausel, Jordi Badosa, Philippe Drobinski
We study short-term prediction of wind speed and wind power (every 10 minutes up to 4 hours ahead).
1 code implementation • 23 Feb 2022 • Jayneel Parekh, Sanjeel Parekh, Pavlo Mozharovskyi, Florence d'Alché-Buc, Gaël Richard
This paper tackles post-hoc interpretability for audio processing networks.
1 code implementation • 8 Feb 2022 • Luc Brogat-Motte, Rémi Flamary, Céline Brouard, Juho Rousu, Florence d'Alché-Buc
This paper introduces a novel and generic framework to solve the flagship task of supervised labeled graph prediction by leveraging Optimal Transport tools.
1 code implementation • 23 Mar 2021 • Guillaume Staerman, Pavlo Mozharovskyi, Pierre Colombo, Stéphan Clémençon, Florence d'Alché-Buc
a probability distribution or a data set.
1 code implementation • 9 Feb 2021 • Alex Lambert, Sanjeel Parekh, Zoltán Szabó, Florence d'Alché-Buc
Style transfer is a significant problem of machine learning with numerous successful applications.
1 code implementation • NeurIPS 2021 • Jayneel Parekh, Pavlo Mozharovskyi, Florence d'Alché-Buc
The interpreter provides both local and global interpretability about the predictive model in terms of human-understandable high level attribute functions, with minimal loss of accuracy.
no code implementations • 29 Jul 2020 • Luc Brogat-Motte, Alessandro Rudi, Céline Brouard, Juho Rousu, Florence d'Alché-Buc
A powerful and flexible approach to structured prediction consists in embedding the structured objects to be predicted into a feature space of possibly infinite dimension by means of output kernels, and then, solving a regression problem in this output space.
no code implementations • 18 Jun 2020 • Guillaume Staerman, Pierre Laforgue, Pavlo Mozharovskyi, Florence d'Alché-Buc
Issued from Optimal Transport, the Wasserstein distance has gained importance in Machine Learning due to its appealing geometrical properties and the increasing availability of efficient approximations.
no code implementations • 27 Mar 2020 • Joelle Pineau, Philippe Vincent-Lamarre, Koustuv Sinha, Vincent Larivière, Alina Beygelzimer, Florence d'Alché-Buc, Emily Fox, Hugo Larochelle
Reproducibility, that is obtaining similar results as presented in a paper or talk, using the same code and data (when available), is a necessary step to verify the reliability of research findings.
no code implementations • 3 Mar 2020 • Dimitri Bouche, Marianne Clausel, François Roueff, Florence d'Alché-Buc
Then, in the more general setting of integral losses based on differentiable ground losses, KPL is implemented using first-order optimization for both fully and partially observed output functions.
no code implementations • ICML 2020 • Pierre Laforgue, Alex Lambert, Luc Brogat-Motte, Florence d'Alché-Buc
Operator-Valued Kernels (OVKs) and associated vector-valued Reproducing Kernel Hilbert Spaces provide an elegant way to extend scalar kernel methods when the output space is a Hilbert space.
no code implementations • IJCNLP 2019 • Alexandre Garcia, Pierre Colombo, Slim Essid, Florence d'Alché-Buc, Chloé Clavel
The task of predicting fine grained user opinion based on spontaneous spoken language is a key problem arising in the development of Computational Agents as well as in the development of social network based opinion miners.
1 code implementation • 9 Apr 2019 • Guillaume Staerman, Pavlo Mozharovskyi, Stephan Clémençon, Florence d'Alché-Buc
For the purpose of monitoring the behavior of complex infrastructures (e. g. aircrafts, transport or energy networks), high-rate sensors are deployed to capture multivariate data, generally unlabeled, in quasi continuous-time to detect quickly the occurrence of anomalies that may jeopardize the smooth operation of the system of interest.
1 code implementation • 26 Feb 2019 • Alexandre Garcia, Slim Essid, Florence d'Alché-Buc, Chloé Clavel
We introduce specific categories in order to make the annotation of opinions easier for movie reviews.
no code implementations • 28 May 2018 • Pierre Laforgue, Stephan Clémençon, Florence d'Alché-Buc
This paper investigates a novel algorithmic approach to data representation based on kernel methods.
no code implementations • 22 May 2018 • Romain Brault, Alex Lambert, Zoltán Szabó, Maxime Sangnier, Florence d'Alché-Buc
A step further consists of learning a continuum of tasks for various loss functions.
no code implementations • ICML 2018 • Alexandre Garcia, Slim Essid, Chloé Clavel, Florence d'Alché-Buc
Motivated by Supervised Opinion Analysis, we propose a novel framework devoted to Structured Output Learning with Abstention (SOLA).
no code implementations • NeurIPS 2016 • Maxime Sangnier, Olivier Fercoq, Florence d'Alché-Buc
Addressing the will to give a more complete picture than an average relationship provided by standard regression, a novel framework for estimating and predicting simultaneously several conditional quantiles is introduced.
no code implementations • 9 May 2016 • Romain Brault, Florence d'Alché-Buc, Markus Heinonen
Devoted to multi-task learning and structured output learning, operator-valued kernels provide a flexible tool to build vector-valued functions in the context of Reproducing Kernel Hilbert Spaces.
no code implementations • 19 Nov 2014 • Markus Heinonen, Florence d'Alché-Buc
Modeling dynamical systems with ordinary differential equations implies a mechanistic view of the process underlying the dynamics.