Here are some of my most recent (2017 -2019) publications and preprints. See here for an exhaustive publication list.
- P. D. Grünwald and R. de Heide and W. Koolen. Safe Testing. Available on arXiv as https://arxiv.org/abs/1906.07801
- P.D. Grünwald and N. Mehta, 2017. Fast Rates for General Unbounded Loss Functions: from ERM to Generalized Bayes. Conditionally accepted for JMLR. Available on arXiv as https://arxiv.org/abs/1605.00252, 2017b.
- Rianne de Heide and Alisa Kirichenko and Nishant Mehta and Peter Grünwald. Safe Bayesian Generalized Linear Regression. Accepted for publication at the International Conference for AI & Statistics (AISTATS 2020). Preliminary version available on arXiv as https://arxiv.org/abs/1910.09227 .
- Z. Mhammedi and P.D. Grünwald and B. Guedj, 2019. PAC-Bayes Unexpected Bernstein Inequality. Proceedings of NeurIPS 2019. Available on arXiv as https://arxiv.org/abs/1905.13367
- P.D. Grünwald and T. Roos. Minimum Description Length Revisited. International Journal of Mathematics for Industry, Nov. 2019.
- J. ter Schure and P. Grünwald, 2019. Accumulation Bias in meta-analysis: the need to consider time in error control. F1000Research 2019, 8:962 (https://doi.org/10.12688/f1000research.19375.1)
- P.D. Grünwald and N. Mehta. A Tight Excess Risk Bound via a Unified PAC-Bayesian-Rademacher-Shtarkov-MDL Complexity. Proceedings ALT (Algorithmic Learning Theory), 2019. Extended version available on arXiv as https://arxiv.org/abs/1710.07732.
- P.D. Grünwald. Safe Probability. Journal of Statistical Planning and Inference 195, 2018, pp. 47-63. Earlier and more complete version available on arXiv as http://arxiv.org/abs/1604.01785.
- P.D. Grünwald and T. van Ommen. Inconsistency of Bayesian Inference for Misspecified Linear Models, and a Proposal for Repairing It . Bayesian Analysis, 2017, pp. 1069-1103. Here is a video recording of a talk I gave about the subject at the NIPS 2014 workshop From Bad Models to Good Policies. And here is a small erratum (one formula was wrong in Section 2.5)