16 citations · 40 across the 14 of their papers we have counts for
14 papers
Deep Sketched Output Kernel Regression for Structured Prediction
Tamim El Ahmad, Junjie Yang, Pierre Laforgue +1
By leveraging the kernel trick in the output space, kernel-induced losses provide a principled way to define structured output prediction tasks for a wide variety of output modalit…
Multitask Online Learning: Listen to the Neighborhood Buzz
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. We introduce $\texttt{MT-CO}_…
Multitask Learning with No Regret: from Improved Confidence Bounds to Active Learning
Pier Giuseppe Sessa, Pierre Laforgue, Nicolò Cesa-Bianchi +1
Multitask learning is a powerful framework that enables one to simultaneously learn multiple related tasks by sharing information between them. Quantifying uncertainty in the estim…
Sketch In, Sketch Out: Accelerating both Learning and Inference for Structured Prediction with Kernels
Tamim El Ahmad, Luc Brogat-Motte, Pierre Laforgue +1
Leveraging the kernel trick in both the input and output spaces, surrogate kernel methods are a flexible and theoretically grounded solution to structured output prediction. If the…
Linear Bandits with Memory: from Rotting to Rising
Giulia Clerici, Pierre Laforgue, Nicolò Cesa-Bianchi
Nonstationary phenomena, such as satiation effects in recommendations, have mostly been modeled using bandits with finitely many arms. However, the richer action space provided by…
On Medians of (Randomized) Pairwise Means
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…
Fast Kernel Methods for Generic Lipschitz Losses via -Sparsified Sketches
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. Sketching, which consists in looking for s…
AdaTask: Adaptive Multitask Online Learning
Pierre Laforgue, Andrea Della Vecchia, Nicolò Cesa-Bianchi +1
We introduce and analyze AdaTask, a multitask online learning algorithm that adapts to the unknown structure of the tasks. When the tasks are stochastically activated, we show…
A Last Switch Dependent Analysis of Satiation and Seasonality in Bandits
Pierre Laforgue, Giulia Clerici, Nicolò Cesa-Bianchi +1
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 no…
Fighting Selection Bias in Statistical Learning: Application to Visual Recognition from Biased Image Databases
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. On the other hand, the recent de…
Multitask Online Mirror Descent
Nicolò Cesa-Bianchi, Pierre Laforgue, Andrea Paudice +1
We introduce and analyze MT-OMD, a multitask generalization of Online Mirror Descent (OMD) which operates by sharing updates between tasks. We prove that the regret of MT-OMD is of…
When OT meets MoM: Robust estimation of Wasserstein Distance
Guillaume Staerman, Pierre Laforgue, Pavlo Mozharovskyi +1
Issued from Optimal Transport, the Wasserstein distance has gained importance in Machine Learning due to its appealing geometrical properties and the increasing availability of eff…
Statistical Learning from Biased Training Samples
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. However, in many practical situat…
Autoencoding any Data through Kernel Autoencoders
Pierre Laforgue, Stephan Clémençon, Florence d'Alché-Buc
This paper investigates a novel algorithmic approach to data representation based on kernel methods. Assuming that the observations lie in a Hilbert space X, the introduced Kernel…