Jean-Francois Ton
University of Oxford
H-index: 10
Europe-United Kingdom
Top articles of Jean-Francois Ton
Overcoming Reward Overoptimization via Adversarial Policy Optimization with Lightweight Uncertainty Estimation
arXiv preprint arXiv:2403.05171
2024/3/8
Dataset Fairness: Achievable Fairness on Your Data With Utility Guarantees
arXiv preprint arXiv:2402.17106
2024/2/27
Jean-Francois Ton
H-Index: 5
Yang Liu
H-Index: 18
Measuring and Reducing LLM Hallucination without Gold-Standard Answers via Expertise-Weighting
arXiv preprint arXiv:2402.10412
2024/2/16
Marginal Density Ratio for Off-Policy Evaluation in Contextual Bandits
Advances in Neural Information Processing Systems
2024/2/13
Rob Cornish
H-Index: 5
Jean-Francois Ton
H-Index: 5
Explaining recommendation systems through contrapositive perturbations
2023/10/13
Fair Classifiers that Abstain without Harm
2024
Deep Concept Removal
arXiv preprint arXiv:2310.05755
2023/10/9
Yegor Klochkov
H-Index: 3
Jean-Francois Ton
H-Index: 5
Ruocheng Guo
H-Index: 13
Yang Liu
H-Index: 18
Hang Li
H-Index: 2
Invariant Learning via Probability of Sufficient and Necessary Causes
Advances in Neural Information Processing Systems
2024/2/13
Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment
arXiv preprint arXiv:2308.05374
2023/8/10
Rectifying unfairness in recommendation feedback loop
SIGIR 2023: Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval
2023
Fair Learning to Rank with Distribution-free Risk Control
arXiv preprint arXiv:2306.07188
2023/6/12
Conformal Off-Policy Prediction in Contextual Bandits
Neurips 2022 (Conference on Neural Information Processing Systems)
2022/6/9
Grassmann Stein Variational Gradient Descent
arxiv arXiv:2202.03297
2022/2/8
Causal reasoning and meta learning using kernel mean embeddings
2022
Jean-Francois Ton
H-Index: 5
Regularized Training of Nearest Neighbor Language Models
arXiv preprint arXiv:2109.08249
2021/9/16
Jean-Francois Ton
H-Index: 5
BayesIMP: Uncertainty Quantification in Causal Data Fusion
2021/6/7
Noise Contrastive Meta-Learning for Conditional Density Estimation using Kernel Mean Embeddings
2021/4/13
Towards a Unified Analysis of Random Fourier Features
JMLR 2021 (Journal of Machine Learning Research)
2021
Jean-Francois Ton
H-Index: 5
Dino Sejdinovic
H-Index: 26
Robust pruning at initialization
International Conference on Learning Representations (ICLR 2021)
2021
Metafun: Meta-learning with iterative functional updates
2020/11/21
Co-Authors
