Publications

Fong, E., Holmes, C. and Walker, S. (2024) “Authors’ reply to the Discussion of ‘Martingale Posterior Distributions’”, Journal of the Royal Statistical Society Series B (Statistical Methodology), 85(5), pp. 1413–1416.

Fong, E., Holmes, C. and Walker, S. (2024) “Martingale posterior distributions”, Journal of the Royal Statistical Society Series B (Statistical Methodology), 85(5), pp. 1357–1391.

Rivera, S. et al. (2024) “Directrices para los protocolos de ensayos clínicos de intervenciones con inteligencia artificial: la extensión SPIRIT-AI”, BULL PAN AM HEALTH ORGAN, 48, p. e12.

Johnson, E., Pike-Burke, C. and Rebeschini, P. (2024) “Sample-efficiency in multi-batch reinforcement learning: the need for dimension-dependent adaptivity”, in Proceedings of the International Conference on Learning Representations (ICLR 2024). OpenReview.

Menacher, A. et al. (2024) “Bayesian lesion estimation with a structured spike-and-slab prior”, Journal of the American Statistical Association, 119(545), pp. 66–80.

Dauncey, S. et al. (2024) “Approximations to the Fisher Information Metric of Deep Generative Models for Out-Of-Distribution Detection”, Transactions on Machine Learning Research, 2024.

Falck, F., Wang, Z. and Holmes, C. (2024) “Is In-Context Learning in Large Language Models Bayesian? A Martingale Perspective”, in Proceedings of Machine Learning Research, pp. 12784–12805.

Clivio, O., Feller, A. and Holmes, C. (2024) “Towards Representation Learning for Weighting Problems in Design-Based Causal Inference”, in Proceedings of Machine Learning Research, pp. 856–880.

Johnson, E., Pike-Burke, C. and Rebeschini, P. (2023) “Optimal convergence rate for exact policy mirror descent in discounted Markov decision processes”, in Advances in Neural Information Processing Systems. NeurIPS, pp. 76496–76524.

Kanade, V., Rebeschini, P. and Vaskevicius, T. (2023) “The statistical complexity of early-stopped mirror descent”, Information and Inference: A Journal of the IMA, 12(4), pp. 3010–3041.