Arthur Gretton

research

∙ 08/08/2023

Kernel Single Proxy Control for Deterministic Confounding

We consider the problem of causal effect estimation with an unobserved c...

0 Liyuan Xu, et al. ∙

research

∙ 07/20/2023

Nonlinear Meta-Learning Can Guarantee Faster Rates

Many recent theoretical works on meta-learning aim to achieve guarantees...

0 Dimitri Meunier, et al. ∙

research

∙ 06/23/2023

Prediction under Latent Subgroup Shifts with High-Dimensional Observations

We introduce a new approach to prediction in graphical models with laten...

0 William I. Walker, et al. ∙

research

∙ 06/14/2023

MMD-FUSE: Learning and Combining Kernels for Two-Sample Testing Without Data Splitting

We propose novel statistics which maximise the power of a two-sample tes...

1 Felix Biggs, et al. ∙

research

∙ 03/08/2023

Deep Hypothesis Tests Detect Clinically Relevant Subgroup Shifts in Medical Images

Distribution shifts remain a fundamental problem for the safe applicatio...

0 Lisa M. Koch, et al. ∙

research

∙ 12/21/2022

Adapting to Latent Subgroup Shifts via Concepts and Proxies

We address the problem of unsupervised domain adaptation when the source...

1 Ibrahim Alabdulmohsin, et al. ∙

research

∙ 12/16/2022

Efficient Conditionally Invariant Representation Learning

We introduce the Conditional Independence Regression CovariancE (CIRCE),...

0 Roman Pogodin, et al. ∙

research

∙ 11/10/2022

Controlling Moments with Kernel Stein Discrepancies

Quantifying the deviation of a probability distribution is challenging w...

0 Heishiro Kanagawa, et al. ∙

research

∙ 10/26/2022

Maximum Likelihood Learning of Energy-Based Models for Simulation-Based Inference

We introduce two synthetic likelihood methods for Simulation-Based Infer...

0 Pierre Glaser, et al. ∙

research

∙ 10/19/2022

A kernel Stein test of goodness of fit for sequential models

We propose a goodness-of-fit measure for probability densities modeling ...

0 Jerome Baum, et al. ∙

research

∙ 10/12/2022

A Neural Mean Embedding Approach for Back-door and Front-door Adjustment

We consider the estimation of average and counterfactual treatment effec...

0 Liyuan Xu, et al. ∙

research

∙ 08/02/2022

Optimal Rates for Regularized Conditional Mean Embedding Learning

We address the consistency of a kernel ridge regression estimate of the ...

0 Zhu Li, et al. ∙

research

∙ 06/18/2022

Efficient Aggregated Kernel Tests using Incomplete U-statistics

We propose a series of computationally efficient, nonparametric tests fo...

8 Antonin Schrab, et al. ∙

research

∙ 02/05/2022

Importance Weighting Approach in Kernel Bayes' Rule

We study a nonparametric approach to Bayesian computation via feature me...

0 Liyuan Xu, et al. ∙

research

∙ 02/02/2022

KSD Aggregated Goodness-of-fit Test

We investigate properties of goodness-of-fit tests based on the Kernel S...

9 Antonin Schrab, et al. ∙

research

∙ 02/01/2022

Deep Layer-wise Networks Have Closed-Form Weights

There is currently a debate within the neuroscience community over the l...

12 Chieh Wu, et al. ∙

research

∙ 11/19/2021

Composite Goodness-of-fit Tests with Kernels

Model misspecification can create significant challenges for the impleme...

0 Oscar Key, et al. ∙

research

∙ 11/06/2021

Kernel Methods for Multistage Causal Inference: Mediation Analysis and Dynamic Treatment Effects

We propose kernel ridge regression estimators for mediation analysis and...

0 Rahul Singh, et al. ∙

research

∙ 10/28/2021

MMD Aggregated Two-Sample Test

We propose a novel nonparametric two-sample test based on the Maximum Me...

3 Antonin Schrab, et al. ∙

research

∙ 06/16/2021

KALE Flow: A Relaxed KL Gradient Flow for Probabilities with Disjoint Support

We study the gradient flow for a relaxed approximation to the Kullback-L...

0 Pierre Glaser, et al. ∙

research

∙ 06/15/2021

Self-Supervised Learning with Kernel Dependence Maximization

We approach self-supervised learning of image representations from a sta...

0 Yazhe Li, et al. ∙

research

∙ 06/07/2021

Deep Proxy Causal Learning and its Application to Confounded Bandit Policy Evaluation

Proxy causal learning (PCL) is a method for estimating the causal effect...

0 Liyuan Xu, et al. ∙

research

∙ 06/06/2021

Towards an Understanding of Benign Overfitting in Neural Networks

Modern machine learning models often employ a huge number of parameters ...

15 Zhu Li, et al. ∙

research

∙ 05/21/2021

On Instrumental Variable Regression for Deep Offline Policy Evaluation

We show that the popular reinforcement learning (RL) strategy of estimat...

26 Yutian Chen, et al. ∙

research

∙ 05/07/2021

Stein's Method Meets Statistics: A Review of Some Recent Developments

Stein's method is a collection of tools for analysing distributional com...

0 Andreas Anastasiou, et al. ∙

research

∙ 12/14/2020

A case for new neural network smoothness constraints

How sensitive should machine learning models be to input changes? We tac...

0 Mihaela Rosca, et al. ∙

research

∙ 11/17/2020

A kernel test for quasi-independence

We consider settings in which the data of interest correspond to pairs o...

0 Tamara Fernández, et al. ∙

research

∙ 11/04/2020

Kernel Dependence Network

We propose a greedy strategy to spectrally train a deep network for mult...

10 Chieh Wu, et al. ∙

research

∙ 10/27/2020

A Weaker Faithfulness Assumption based on Triple Interactions

One of the core assumptions in causal discovery is the faithfulness assu...

0 Alexander Marx, et al. ∙

research

∙ 10/14/2020

Learning Deep Features in Instrumental Variable Regression

Instrumental variable (IV) regression is a standard strategy for learnin...

21 Liyuan Xu, et al. ∙

research

∙ 10/12/2020

Efficient Wasserstein Natural Gradients for Reinforcement Learning

A novel optimization approach is proposed for application to policy grad...

0 Ted Moskovitz, et al. ∙

research

∙ 10/10/2020

Kernel Methods for Policy Evaluation: Treatment Effects, Mediation Analysis, and Off-Policy Planning

We propose a novel framework for non-parametric policy evaluation in sta...

0 Rahul Singh, et al. ∙

research

∙ 08/19/2020

Kernelized Stein Discrepancy Tests of Goodness-of-fit for Time-to-Event Data

Survival Analysis and Reliability Theory are concerned with the analysis...

0 Tamara Fernández, et al. ∙

research

∙ 06/17/2020

A Non-Asymptotic Analysis for Stein Variational Gradient Descent

We study the Stein Variational Gradient Descent (SVGD) algorithm, which ...

13 Anna Korba, et al. ∙

research

∙ 06/15/2020

Layer-wise Learning of Kernel Dependence Networks

We propose a greedy strategy to train a deep network for multi-class cla...

17 Chieh Wu, et al. ∙

research

∙ 03/10/2020

KALE: When Energy-Based Learning Meets Adversarial Training

Legendre duality provides a variational lower-bound for the Kullback-Lei...

13 Michael Arbel, et al. ∙

research

∙ 02/21/2020

Learning Deep Kernels for Non-Parametric Two-Sample Tests

We propose a class of kernel-based two-sample tests, which aim to determ...

17 Feng Liu, et al. ∙

research

∙ 12/08/2019

A kernel log-rank test of independence for right-censored data

With the incorporation of new data gathering methods in clinical researc...

9 Tamara Fernández, et al. ∙

research

∙ 10/21/2019

Kernelized Wasserstein Natural Gradient

Many machine learning problems can be expressed as the optimization of s...

13 Michael Arbel, et al. ∙

research

∙ 08/20/2019

Counterfactual Distribution Regression for Structured Inference

We consider problems in which a system receives external perturbations f...

5 Nicolo Colombo, et al. ∙

research

∙ 07/01/2019

A Kernel Stein Test for Comparing Latent Variable Models

We propose a nonparametric, kernel-based test to assess the relative goo...

6 Heishiro Kanagawa, et al. ∙

research

∙ 06/11/2019

Maximum Mean Discrepancy Gradient Flow

We construct a Wasserstein gradient flow of the maximum mean discrepancy...

0 Michael Arbel, et al. ∙

research

∙ 06/01/2019

Kernel Instrumental Variable Regression

Instrumental variable regression is a strategy for learning causal relat...

14 Rahul Singh, et al. ∙

research

∙ 04/27/2019

Exponential Family Estimation via Adversarial Dynamics Embedding

We present an efficient algorithm for maximum likelihood estimation (MLE...

28 Bo Dai, et al. ∙

research

∙ 11/20/2018

Learning deep kernels for exponential family densities

The kernel exponential family is a rich class of distributions,which can...

46 Li Wenliang, et al. ∙

research

∙ 11/06/2018

Kernel Exponential Family Estimation via Doubly Dual Embedding

We investigate penalized maximum log-likelihood estimation for exponenti...

4 Bo Dai, et al. ∙

research

∙ 10/27/2018

Informative Features for Model Comparison

Given two candidate models, and a set of target observations, we address...

0 Wittawat Jitkrittum, et al. ∙

research

∙ 10/09/2018

A maximum-mean-discrepancy goodness-of-fit test for censored data

We introduce a kernel-based goodness-of-fit test for censored data, wher...

0 Tamara Fernández, et al. ∙

research

∙ 07/01/2018

Antithetic and Monte Carlo kernel estimators for partial rankings

In the modern age, rankings data is ubiquitous and it is useful for a va...

2 María Lomelí, et al. ∙

research

∙ 05/29/2018

On gradient regularizers for MMD GANs

We propose a principled method for gradient-based regularization of the ...

6 Michael Arbel, et al. ∙

Arthur Gretton

Featured Co-authors