Suivre
Pierre Laforgue
Titre
Citée par
Citée par
Année
When ot meets mom: Robust estimation of wasserstein distance
G Staerman, P Laforgue, P Mozharovskyi, F d’Alché-Buc
International Conference on Artificial Intelligence and Statistics, 136-144, 2021
202021
Autoencoding any data through kernel autoencoders
P Laforgue, S Clémençon, F d’Alché-Buc
The 22nd International Conference on Artificial Intelligence and Statistics …, 2019
162019
Duality in RKHSs with infinite dimensional outputs: Application to robust losses
P Laforgue, A Lambert, L Brogat-Motte, F d’Alché-Buc
International Conference on Machine Learning, 5598-5607, 2020
14*2020
On Medians of (Randomized) Pairwise Means
P Laforgue, S Clémençon, P Bertail
International Conference on Machine Learning, 1272-1281, 2019
102019
Generalization bounds in the presence of outliers: a median-of-means study
P Laforgue, G Staerman, S Clémençon
International Conference on Machine Learning, 5937-5947, 2021
8*2021
Statistical Learning from Biased Training Samples
P Laforgue, S Clémençon
arXiv preprint arXiv:1906.12304, 2019
8*2019
A last switch dependent analysis of satiation and seasonality in bandits
P Laforgue, G Clerici, N Cesa-Bianchi, R Gilad-Bachrach
International Conference on Artificial Intelligence and Statistics, 971-990, 2022
3*2022
Multitask online mirror descent
N Cesa-Bianchi, P Laforgue, A Paudice, M Pontil
arXiv preprint arXiv:2106.02393, 2021
32021
AdaTask: Adaptive Multitask Online Learning
P Laforgue, A Della Vecchia, N Cesa-Bianchi, L Rosasco
arXiv preprint arXiv:2205.15802, 2022
12022
-Sparsified Sketches for Fast Multiple Output Kernel Methods
TE Ahmad, P Laforgue, F d'Alché-Buc
arXiv preprint arXiv:2206.03827, 2022
2022
Statistical learning from biased training samples
S Clémençon, P Laforgue
Electronic Journal of Statistics 16 (2), 6086-6134, 2022
2022
Fighting Selection Bias in Statistical Learning: Application to Visual Recognition from Biased Image Databases
S Clémençon, P Laforgue, R Vogel
arXiv preprint arXiv:2109.02357, 2021
2021
Visual Recognition with Deep Learning from Biased Image Datasets
R Vogel, S Clémençon, P Laforgue
arXiv e-prints, arXiv: 2109.02357, 2021
2021
Deep kernel representation learning for complex data and reliability issues
P Laforgue
Institut polytechnique de Paris, 2020
2020
Le système ne peut pas réaliser cette opération maintenant. Veuillez réessayer plus tard.
Articles 1–14