1.2k citations
- Centre National de la Recherche ScientifiqueFR14 papers
- Institut national de recherche en sciences et technologies du numériqueFR14 papers
- National Institute of InformaticsJP13 papers
- SupélecFR13 papers
- University of Illinois ChicagoUS10 papers
- Technical University of MunichDE9 papers
- Laboratoire Informatique d'AvignonFR8 papers
- University College LondonGB8 papers
- University of EdinburghGB8 papers
- Sorbonne UniversitéFR7 papers
- Université Côte d'AzurFR7 papers
- University of Eastern FinlandFI7 papers
22 papers · 1 filter
Zero-shot Model-based Reinforcement Learning using Large Language Models
Abdelhakim Benechehab, Youssef Attia El Hili, Ambroise Odonnat +6
The emerging zero-shot capabilities of Large Language Models (LLMs) have led to their applications in areas extending well beyond natural language processing tasks. In reinforcemen…
Fast Computation of Leave-One-Out Cross-Validation for -NN Regression
Motonobu Kanagawa
We describe a fast computation method for leave-one-out cross-validation (LOOCV) for -nearest neighbours (-NN) regression. We show that, under a tie-breaking condition for ne…
When is Importance Weighting Correction Needed for Covariate Shift Adaptation?
Davit Gogolashvili, Matteo Zecchin, Motonobu Kanagawa +2
This paper investigates when the importance weighting (IW) correction is needed to address covariate shift, a common situation in supervised learning where the input distributions…
How Much is Enough? A Study on Diffusion Times in Score-based Generative Models
Giulio Franzese, Simone Rossi, Lixuan Yang +4
Score-based diffusion models are a class of generative models whose dynamics is described by stochastic differential equations that map noise into data. While recent works have sta…
Complex-to-Real Sketches for Tensor Products with Applications to the Polynomial Kernel
Jonas Wacker, Ruben Ohana, Maurizio Filippone
Randomized sketches of a tensor product of vectors follow a tradeoff between statistical efficiency and computational acceleration. Commonly used approaches avoid computing the…
Model Selection for Bayesian Autoencoders
Ba-Hien Tran, Simone Rossi, Dimitrios Milios +3
We develop a novel method for carrying out model selection for Bayesian autoencoders (BAEs) by means of prior hyper-parameter optimization. Inspired by the common practice of type-…