Zobrazeno 1 - 10
of 1 882
pro vyhledávání: '"Gretton, A"'
Autor:
Sgouritsa, Eleni, Aglietti, Virginia, Teh, Yee Whye, Doucet, Arnaud, Gretton, Arthur, Chiappa, Silvia
The reasoning abilities of Large Language Models (LLMs) are attracting increasing attention. In this work, we focus on causal reasoning and address the task of establishing causal relationships based on correlation information, a highly challenging p
Externí odkaz:
http://arxiv.org/abs/2412.13952
We study the kernel instrumental variable algorithm of \citet{singh2019kernel}, a nonparametric two-stage least squares (2SLS) procedure which has demonstrated strong empirical performance. We provide a convergence analysis that covers both the ident
Externí odkaz:
http://arxiv.org/abs/2411.19653
Accurate uncertainty quantification for causal effects is essential for robust decision making in complex systems, but remains challenging in non-parametric settings. One promising framework represents conditional distributions in a reproducing kerne
Externí odkaz:
http://arxiv.org/abs/2410.14483
We introduce credal two-sample testing, a new hypothesis testing framework for comparing credal sets -- convex sets of probability measures where each element captures aleatoric uncertainty and the set itself represents epistemic uncertainty that ari
Externí odkaz:
http://arxiv.org/abs/2410.12921
Autor:
Chen, Zonghao, Mustafi, Aratrika, Glaser, Pierre, Korba, Anna, Gretton, Arthur, Sriperumbudur, Bharath K.
We introduce a (de)-regularization of the Maximum Mean Discrepancy (DrMMD) and its Wasserstein gradient flow. Existing gradient flows that transport samples from source distribution to target distribution with only target samples, either lack tractab
Externí odkaz:
http://arxiv.org/abs/2409.14980
In reinforcement learning (RL), the consideration of multivariate reward signals has led to fundamental advancements in multi-objective decision-making, transfer learning, and representation learning. This work introduces the first oracle-free and co
Externí odkaz:
http://arxiv.org/abs/2409.00328
We address the problem of causal effect estimation where hidden confounders are present, with a focus on two settings: instrumental variable regression with additional observed confounders, and proxy causal learning. Our approach uses a singular valu
Externí odkaz:
http://arxiv.org/abs/2407.10448
Autor:
Schrouff, Jessica, Bellot, Alexis, Rannen-Triki, Amal, Malek, Alan, Albuquerque, Isabela, Gretton, Arthur, D'Amour, Alexander, Chiappa, Silvia
Failures of fairness or robustness in machine learning predictive settings can be due to undesired dependencies between covariates, outcomes and auxiliary factors of variation. A common strategy to mitigate these failures is data balancing, which att
Externí odkaz:
http://arxiv.org/abs/2406.17433
Publikováno v:
Conference on Uncertainty in Artificial Intelligence (UAI) 2024
We propose a novel approach for estimating conditional or parametric expectations in the setting where obtaining samples or evaluating integrands is costly. Through the framework of probabilistic numerical methods (such as Bayesian quadrature), our n
Externí odkaz:
http://arxiv.org/abs/2406.16530
We study theoretical properties of a broad class of regularized algorithms with vector-valued output. These spectral algorithms include kernel ridge regression, kernel principal component regression, various implementations of gradient descent and ma
Externí odkaz:
http://arxiv.org/abs/2405.14778