Publications
This page contains my publications and related documents. The best publicly available version for each paper can be found by clicking on its title. Bibliographic information is available in this BibTeX file. You can be alerted to new publications using the ‘Follow’ button on my Google scholar profile.
Like many Dutch names, my family name ‘Van Erven’ consists of multiple words. In the Netherlands, the prefix ‘van’ is capitalised, except when directly preceded by a given name (e.g. Tim) or initials.
Preprints and Pending Submissions
-
An Online Feasible Point Method for Benign Generalized Nash Equilibrium Problems
S. Sachs, H. Hadiji, T. van Erven and M. Staudigl. Preprint, 2024. -
Accelerated Rates between Stochastic and Adversarial Online Convex Optimization
S. Sachs, H. Hadiji, T. van Erven and C. Guzmán. Preprint, 2023.
Refereed Publications
-
The Risks of Recourse in Binary Classification
H. Fokkema, D. Garreau and T. van Erven. Proceedings of the 27th International Conference on Artificial Intelligence and Statistics (AISTATS), vol. 238, pp. 550-558, 2024. [slides] -
Towards Characterizing the First-order Query Complexity of Learning (Approximate) Nash Equilibria in Zero-sum Matrix Games
H. Hadiji, S. Sachs, T. van Erven and W. M. Koolen. Advances in Neural Information Processing Systems (NeurIPS), vol. 36, pp. 13356-13373, 2023. [slides] -
First- and Second-Order Bounds for Adversarial Linear Contextual Bandits
J. Olkhovskaya, J. Mayo, T. van Erven, G. Neu and C. Wei. Advances in Neural Information Processing Systems (NeurIPS), vol. 36, pp. 61625-61644, 2023. -
Adaptive Selective Sampling for Online Prediction with Experts
R. M. Castro, F. Hellström and T. van Erven. Advances in Neural Information Processing Systems (NeurIPS), vol. 36, pp. 134-154, 2023. -
Attribution-based Explanations that Provide Recourse Cannot be Robust
H. Fokkema, R. de Heide and T. van Erven. Journal of Machine Learning Research, vol. 24, no. 360, pp. 1-37, 2023. [slides] -
Generalization Guarantees via Algorithm-dependent Rademacher Complexity
S. Sachs, T. van Erven, L. Hodgkinson, R. Khanna and U. Şimşekli. Proceedings of Machine Learning Research, vol. 195: Thirty Sixth Conference on Learning Theory (COLT), pp. 4863-4880, 2023. [slides] -
Between Stochastic and Adversarial Online Convex Optimization: Improved Regret Bounds via Smoothness
S. Sachs, H. Hadiji, T. van Erven and C. Guzmán. Advances in Neural Information Processing Systems (NeurIPS), pp. 691-702, 2022. -
Scale-free Unconstrained Online Learning for Curved Losses
J. J. Mayo, H. Hadiji and T. van Erven. Proceedings of the 35th Conference on Learning Theory (COLT), vol. 178, pp. 4464-4497, 2022. -
Distributed Online Learning for Joint Regret with Communication Constraints
D. van der Hoeven, H. Hadiji and T. van Erven. Proceedings of the 33rd International Conference on Algorithmic Learning Theory (ALT), vol. 167, pp. 1003-1042, 2022. -
MetaGrad: Adaptation using Multiple Learning Rates in Online Learning
T. van Erven, W. M. Koolen and D. van der Hoeven. Journal of Machine Learning Research, vol. 22, no. 161, pp. 1-61, 2021. -
Robust Online Convex Optimization in the Presence of Outliers
T. van Erven, S. Sachs, W. M. Koolen and W. Kotłowski. Proceedings of the 34th Conference on Learning Theory (COLT), vol. 134, pp. 4174-4194, 2021. [blog post, COLT talks, slides] -
Fast Exact Bayesian Inference for Sparse Signals in the Normal Sequence Model
T. van Erven and B. Szabó. Bayesian Analysis, vol. 16, no. 3, pp. 933-960, 2021. [R package] -
Open Problem: Fast and Optimal Online Portfolio Selection
T. van Erven, D. van der Hoeven, W. Kotłowski and W. M. Koolen. Proceedings of Machine Learning Research, vol. 125: Conference on Learning Theory (COLT), pp. 3864-3869, 2020. Status: Solved by Zimmert, Agarwal, Kale. [COLT talk] -
Lipschitz Adaptivity with Multiple Learning Rates in Online Learning
Z. Mhammedi, W. M. Koolen and T. van Erven. Proceedings of Machine Learning Research, vol. 99: Conference on Learning Theory (COLT), pp. 2490-2511, 2019. -
The Many Faces of Exponential Weights in Online Learning
D. van der Hoeven, T. van Erven and W. Kotłowski. Proceedings of Machine Learning Research, vol. 35: Proceedings of the 31st Conference on Learning Theory (COLT), pp. 2067-2092, 2018. [slides] -
MetaGrad: Multiple Learning Rates in Online Learning
T. van Erven and W. M. Koolen. Advances in Neural Information Processing Systems 29 (NeurIPS), pp. 3666-3674, 2016. [NeurIPS slides, UvA slides, Matlab code] -
Combining Adversarial Guarantees and Stochastic Fast Rates in Online Learning
W. M. Koolen, P. Grünwald and T. van Erven. Advances in Neural Information Processing Systems 29 (NeurIPS), pp. 4457-4465, 2016. -
Fast Rates in Statistical and Online Learning
T. van Erven, P. D. Grünwald, N. A. Mehta, M. D. Reid and R. C. Williamson. Journal of Machine Learning Research, vol. 16, pp. 1793-1861, 2015. In the special issue dedicated to the memory of Alexey Chervonenkis. [Inria slides] -
Second-order Quantile Methods for Experts and Combinatorial Games
W. M. Koolen and T. van Erven. JMLR Workshop and Conference Proceedings, vol. 40: Proceedings of the 28th Conference on Learning Theory (COLT), pp. 1155-1175, 2015. [code, Wouter's blog post 1, post 2] -
Game-theoretically Optimal Reconciliation of Contemporaneous Hierarchical Time Series Forecasts
T. van Erven and J. Cugliari. Modeling and Stochastic Learning for Forecasting in High Dimensions, pp. 297-317, 2015. The older WIPFOR workshop version has slides. [R package, official version] -
Rényi Divergence and Kullback-Leibler Divergence
T. van Erven and P. Harremoës. IEEE Transactions on Information Theory, vol. 60, no. 7, pp. 3797-3820, 2014. [official version, errata] -
Follow the Leader with Dropout Perturbations
T. van Erven, W. Kotłowski and M. K. Warmuth. JMLR Workshop and Conference Proceedings, vol. 35: Proceedings of the 27th Conference on Learning Theory (COLT), pp. 949-974, 2014. [video lecture, slides] -
A Second-order Bound with Excess Losses
P. Gaillard, G. Stoltz and T. van Erven. JMLR Workshop and Conference Proceedings, vol. 35: Proceedings of the 27th Conference on Learning Theory (COLT), pp. 176-196, 2014. [video lecture] -
Learning the Learning Rate for Prediction with Expert Advice
W. M. Koolen, T. van Erven and P. D. Grünwald. Advances in Neural Information Processing Systems 27 (NeurIPS), pp. 2294-2302, 2014. -
Follow the Leader If You Can, Hedge If You Must
S. de Rooij, T. van Erven, P. D. Grünwald and W. M. Koolen. Journal of Machine Learning Research, vol. 15, pp. 1281-1316, 2014. [slides] -
Mixability in Statistical Learning
T. van Erven, P. D. Grünwald, M. D. Reid and R. C. Williamson. Advances in Neural Information Processing Systems 25 (NeurIPS 2012), pp. 1691-1699, 2012. [slides, poster] -
Catching up faster by switching sooner: A predictive approach to adaptive estimation with an application to the AIC-BIC dilemma
T. van Erven, P. Grünwald and S. de Rooij. Journal of the Royal Statistical Society, Series B, vol. 74, no. 3, pp. 361-417, 2012. Read at the ordinary meeting on October 19, 2011. An earlier version of this paper was runner-up in the student paper competition of the Risk Analysis Section of the ASA. [Matlab code, official version with discussion, slides, Peter's UAI talk] -
Mixability is Bayes Risk Curvature Relative to Log Loss
T. van Erven, M. D. Reid and R. C. Williamson. Journal of Machine Learning Research, vol. 13, pp. 1639-1663, 2012. This is an extended version of our COLT 2011 paper, with an improved presentation and several new results. -
Adaptive Hedge
T. van Erven, P. D. Grünwald, W. Koolen and S. de Rooij. Advances in Neural Information Processing Systems 24 (NeurIPS 2011), 2011. -
Mixability is Bayes Risk Curvature Relative to Log Loss
T. van Erven, M. D. Reid and R. C. Williamson. Proceedings of the 24th Annual Conference on Learning Theory (COLT), 2011. -
Rényi Divergence and Majorization
T. van Erven and P. Harremoës. IEEE International Symposium on Information Theory (ISIT), pp. 1335-1339, 2010. -
Learning the Switching Rate by Discretising Bernoulli Sources Online
S. de Rooij and T. van Erven. Proceedings of the Twelfth International Conference on Artificial Intelligence and Statistics (AISTATS), vol. 5, pp. 432-439, 2009. -
Catching Up Faster in Bayesian Model Selection and Model Averaging
T. van Erven, P. D. Grünwald and S. de Rooij. Advances in Neural Information Processing Systems 20 (NeurIPS 2007), 2008. [NeurIPS poster]
PhD Thesis
-
When Data Compression and Statistics Disagree: Two Frequentist Challenges for the Minimum Description Length Principle
T. van Erven. PhD thesis, Leiden University, 2010. Promotor: Peter Grünwald.
Other
Unrefereed publications, publications at local conferences, and unpublished work
-
Explaining Predictions by Approximating the Local Decision Boundary
G. Vlassopoulos, T. van Erven, H. Brighton and V. Menkovski. Unpublished, 2020. -
PAC-Bayes Mini-tutorial: A Continuous Union Bound
T. van Erven. Unpublished, 2014. -
Making Regional Forecasts Add Up
T. van Erven and J. Cugliari. Extended abstract for the Workshop on Industry & Practices for Forecasting (WIPFOR), 2013. [slides] -
Switching between Hidden Markov Models using Fixed Share
W. M. Koolen and T. van Erven. Unpublished, 2010. -
Freezing and Sleeping: Tracking Experts that Learn by Evolving Past Posteriors
W. M. Koolen and T. van Erven. Unpublished, 2010. -
Catching Up Faster by Switching Sooner: A Prequential Solution to the AIC-BIC Dilemma
T. van Erven, P. D. Grünwald and S. de Rooij. Preprint posted on the math arXiv, arXiv:0807.1005 [math.ST], July 2008. Runner-up in the student paper competition of the Risk Analysis Section of the ASA. -
Switching between Predictors with an Application in Density Estimation
T. van Erven, S. de Rooij and P. Grünwald. Proceedings of the 28th Symposium on Information Theory in the Benelux, Enschede, The Netherlands, 2007. -
The Momentum Problem in MDL and Bayesian Prediction
T. van Erven. Master's thesis, University of Amsterdam, The Netherlands, May 2006. Supervisors: Peter Grünwald, Steven de Rooij. [tex]