no code implementations • 26 Oct 2023 • Juliette Achddou, Nicolò Cesa-Bianchi, Pierre Laforgue
We study multitask online learning in a setting where agents can only exchange information with their neighbors on an arbitrary communication network.
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 Feb 2023 • Giulia Clerici, Pierre Laforgue, Nicolò Cesa-Bianchi
By choosing the cycle length so as to trade-off approximation and estimation errors, we then prove a bound of order $\sqrt{d}\,(m+1)^{\frac{1}{2}+\max\{\gamma, 0\}}\, T^{3/4}$ (ignoring log factors) on the regret against the optimal sequence of actions, where $T$ is the horizon and $d$ is the dimension of the linear action space.
no code implementations • 1 Nov 2022 • Pierre Laforgue, Stephan Clémençon, Patrice Bertail
Tournament procedures, recently introduced in Lugosi & Mendelson (2016), offer an appealing alternative, from a theoretical perspective at least, to the principle of Empirical Risk Minimization in machine learning.
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 • 31 May 2022 • Pierre Laforgue, Andrea Della Vecchia, Nicolò Cesa-Bianchi, Lorenzo Rosasco
We introduce and analyze AdaTask, a multitask online learning algorithm that adapts to the unknown structure of the tasks.
1 code implementation • 22 Oct 2021 • Pierre Laforgue, Giulia Clerici, Nicolò Cesa-Bianchi, Ran Gilad-Bachrach
Motivated by the fact that humans like some level of unpredictability or novelty, and might therefore get quickly bored when interacting with a stationary policy, we introduce a novel non-stationary bandit problem, where the expected reward of an arm is fully determined by the time elapsed since the arm last took part in a switch of actions.
no code implementations • 6 Sep 2021 • Stephan Clémençon, Pierre Laforgue, Robin Vogel
In practice, and especially when training deep neural networks, visual recognition rules are often learned based on various sources of information.
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.
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 • 9 Jun 2020 • Pierre Laforgue, Guillaume Staerman, Stephan Clémençon
In contrast to the empirical mean, the Median-of-Means (MoM) is an estimator of the mean $\theta$ of a square integrable r. v.
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 • 28 Jun 2019 • Stephan Clémençon, Pierre Laforgue
With the deluge of digitized information in the Big Data era, massive datasets are becoming increasingly available for learning predictive models.
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.