Here is a list including most research-related publications and preprints written by myself and colleagues.
Robust variance-regularized risk minimization with concomitant scaling
Matthew J. Holland
Preprint.
[pdf, abstract, code]
Flexible risk design using bi-directional dispersion
Matthew J. Holland
Presented at AISTATS 2023.
Proceedings of Machine Learning Research 206:1586-1623, 2023.
[pdf, proceedings, code]
Learning criteria going beyond the usual risk
Matthew J. Holland and Kazuki Tanabe
Preprint.
[pdf, abstract]
Learning with risks based on M-location
Matthew J. Holland
Journal: Machine Learning, 111:4679–4718, 2022.
Oral: ECML-PKDD 2022, Grenoble, France.
[pdf, abstract, doi, code]
Spectral risk-based learning using unbounded losses
Matthew J. Holland and El Mehdi Haress
Presented at AISTATS 2022.
Proceedings of Machine Learning Research 151:1871-1886, 2022.
[pdf, proceedings, code]
Anytime Guarantees under Heavy-Tailed Data
Matthew J. Holland
Presented at AAAI 2022.
Proceedings of the AAAI Conference on Artificial Intelligence, 36(6):6918-6925.
[pdf, proceedings, code]
Making learning more transparent using conformalized performance prediction
Matthew J. Holland
Presented at ICML 2021, Workshop on Distribution-Free Uncertainty Quantification.
[pdf, abstract]
Learning with risk-averse feedback under potentially heavy tails
Matthew J. Holland and El Mehdi Haress
Presented at AISTATS 2021.
Proceedings of Machine Learning Research 130:892-900, 2021.
[pdf, proceedings, code]
Robustness and scalability under heavy tails, without strong convexity
Matthew J. Holland
Presented at AISTATS 2021.
Proceedings of Machine Learning Research 130:865-873, 2021.
[pdf, proceedings, code]
Scaling-Up Robust Gradient Descent Techniques
Matthew J. Holland
Presented at AAAI 2021.
Proceedings of the AAAI Conference on Artificial Intelligence, 35(9):7694-7701.
[pdf, proceedings, code]
Better scalability under potentially heavy-tailed feedback
Matthew J. Holland
Archival version.
[pdf, abstract, code]
PAC-Bayes under potentially heavy tails
Matthew J. Holland
Presented at NeurIPS 2019.
Advances in Neural Information Processing Systems 32, 2020.
[pdf, proceedings]
Distribution-robust mean estimation via smoothed random perturbations
Matthew J. Holland
Preprint.
[pdf, abstract, code]
Better generalization with less data using robust gradient descent
Matthew J. Holland and Kazushi Ikeda
Presented at ICML 2019.
Proceedings of Machine Learning Research 97:2761-2770, 2019.
[pdf, abstract]
Robust gradient descent via back-propagation: A Chainer-based tutorial
Matthew J. Holland
[pdf, code]
Efficient learning with robust gradient descent
Matthew J. Holland and Kazushi Ikeda
Journal: Machine Learning, 108(8):1523-1560, 2019.
Oral: ECML-PKDD 2019, Wurzburg, Germany.
[pdf, abstract, doi]
Robust descent using smoothed multiplicative noise
Matthew J. Holland
Presented at AISTATS 2019.
Proceedings of Machine Learning Research 89:703-711, 2019.
[pdf, abstract]
Classification using margin pursuit
Matthew J. Holland
Presented at AISTATS 2019.
Proceedings of Machine Learning Research 89:712-720, 2019.
[pdf, abstract, code]
Robust regression using biased objectives
Matthew J. Holland and Kazushi Ikeda
Journal: Machine Learning, 106(9):1643-1679, 2017.
Oral: ECML-PKDD 2017, Skopje, Macedonia.
[pdf, doi, code]
Minimum proper loss estimators for parametric models
Matthew J. Holland and Kazushi Ikeda
IEEE Transactions on Signal Processing, 64(3):704-713, 2016.
[pdf, data, doi]
Location robust estimation of predictive Weibull parameters in short-term wind speed forecasting
Matthew J. Holland and Kazushi Ikeda
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2015.
[pdf, doi]
Forecasting in wind energy applications with site-adaptive Weibull estimation
Matthew J. Holland and Kazushi Ikeda
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2014.
[pdf, doi]