7 papers
Minimax estimation of the pseudo-spectral gap of continuous Markov chains, with applications to empirical concentration bounds
Vahe Karagulyan, Mikołaj Kasprzak, Pierre Alquier
We study the minimax estimation of the pseudo-spectral gap of a Markov chain from the observation of a single trajectory. Extending earlier works on finite-state space cha…
Position: agentic AI orchestration should be Bayes-consistent
Theodore Papamarkou, Pierre Alquier, Matthias Bauer +27
LLMs excel at predictive tasks and complex reasoning tasks, but many high-value deployments rely on decisions under uncertainty, for example, which tool to call, which expert to co…
Estimation of time series by Maximum Mean Discrepancy
Pierre Alquier, Jean-David Fermanian, Benjamin Poignard
We define two minimum distance estimators for dependent data by minimizing some approximated Maximum Mean Discrepancy distances between the true empirical distribution of observati…
Empirical PAC-Bayes Bounds for Markov Chains
Vahe Karagulyan, Pierre Alquier
The core of generalization theory was developed for independent observations. Some PAC and PAC-Bayes bounds are available for data that exhibit a temporal dependence. However, ther…
regMMD: An R package for parametric estimation and regression with maximum mean discrepancy
Pierre Alquier, Mathieu Gerber
The Maximum Mean Discrepancy (MMD) is a kernel-based metric widely used for nonparametric tests and estimation. Recently, it has also been studied as an objective function for para…
Minimax optimality of deep neural networks on dependent data via PAC-Bayes bounds
Pierre Alquier, William Kengne
In a groundbreaking work, Schmidt-Hieber (2020) proved the minimax optimality of deep neural networks with ReLu activation for least-square regression estimation over a large class…
Logarithmic Smoothing for Pessimistic Off-Policy Evaluation, Selection and Learning
Otmane Sakhi, Imad Aouali, Pierre Alquier +1
This work investigates the offline formulation of the contextual bandit problem, where the goal is to leverage past interactions collected under a behavior policy to evaluate, sele…