About Me

Currently working as senior research scientist at Tiktok, focusing on explainable ML and causal inference.

We are hiring PhD interns !!! Link. Feel free to contact me for more information.

I recently defended my DPhil at the University of Oxford in Machine Learning supervised by Prof. Yee Whye Teh and Prof. Dino Sejdinovic. Before joining the Oxford Statistical Machine Learning Group, I did my MSc in Applied Statistics at the University of Oxford. Prior to that, I graduated with BSc in Mathematics from Imperial College London.


I have previously interned at Amazon Tubingen Germany, Apple Inc. Cupertino CA. and Bloomberg L.P. London. My research interest lies in Causal Inference, XAI and Kernel Methods. Specifically, understanding uncertainty in Deep/Causal Models.

Most Recent Work

meta

Conformal Off-Policy Prediction in Contextual Bandits

Jean-Francois Ton*, Muhammad Faaiz Taufiq*, Rob Cornish, Yee Whye Teh, Arnaud Doucet

14/9/2022

Our paper has been accepted at Neurips 2022 Link.

meta

Grassmann Stein Variational Gradient Descent

Xing Liu, Harrison Zhu, Jean-Francois Ton, George Wynne, Andrew Duncan

19/1/2022

Our paper has been accepted at AISTATS 2022 Link .

meta

BayesIMP: Uncertainty Quantification for Causal Data Fusion

Jean-Francois Ton*, Siu Lun Chau*, Javier Gonzalez, Yee Whye Teh, Dino Sejdinovic

03/10/2021

Our paper has been accepted at Neurips 2021 Link.

meta

Regularized Training of Nearest Neighbor Language Models

Jean-Francois Ton, Walter Talbott, Shuangfei Zhai, Josh Susskind

03/10/2021

Our paper has been accepted at NAACL 2022 SRW Link.

meta

Noise Contrastive Meta Learning for Conditional Density Estimation using Kernel Mean Embeddings

Jean-Francois Ton, Lucian Chan, Yee Whye Teh, Dino Sejdinovic

05/06/2019

Our paper has been accepted at AISTATS 2021 Link.

meta

Pruning untrained neural networks : Principles and Analysis

Soufiane Hayou, Jean-Francois Ton, Arnaud Doucet, Yee Whye Teh

21/02/2020

Our paper has been accepted at ICLR 2021 Link.

meta

Meta Learning for Causal Direction

Jean-Francois Ton, Dino Sejdinovic, Kenji Fukumizu

14/12/2020

Our paper has been accepted at AAAI 2021 Link.

meta

MetaFun: Meta-Learning with Iterative Functional Updates

Jin Xu, Jean-Francois Ton, Hyunjik Kim, Adam R. Kosiorek, Yee Whye Teh

05/12/2019

Our paper has been accepted at ICML 2020 Link.

BQ

Automated Model Selection Using Bayesian Quadrature

Henry Chai, Jean-Francois Ton, Roman Garnett, Michael A. Osborne

26/02/2019

Our paper has been accepted at ICML 2019 Link

Non-stationary GP

Spatial Mapping with Gaussian Processes and Nonstationary Fourier Features

Jean-Francois Ton, Seth Flaxman, Dino Sejdinovic, Samir Bhatt

09/07/2018

Our paper has been accepted at Spatatial Statisics Journal 2018 Journal of Spatial Statistics 2018

kernel

A Unified Analysis of Random Fourier Features

Zhu Li,Jean-Francois Ton, Dino Oglic, Dino Sejdinovic

09/12/2017

Our paper has been accepted at ICML 2019 (Honorable Mention for Best Paper Award) Link

Research interests

My main interests lie in Computational Statistics and Machine Learning. I have done projects on MCMC Methods, Gaussian Processes, Bayesian Quadrature and Bayesian Deep Learning. I am currently working on Meta-Learning and in understanding uncertainty in Deep Learning Models. In my free time I like to do photography and play table tennis.

Curriculum vitae

My Résumé is available here.

Contact me

Email

jeanfrancois-at-bytedance.com

Post

Department of Statistics
University of Oxford
24-29 St Giles
Oxford OX1 3LB, UK