Matthew J. Holland

According to our database, Matthew J. Holland authored at least 27 papers between 2014 and 2024.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2024

Criterion collapse and loss distribution control.

Matthew J. Holland

CoRR, 2024

Robust variance-regularized risk minimization with concomitant scaling.

Matthew J. Holland

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2024

A Survey of Learning Criteria Going beyond the Usual Risk (Abstract Reprint).

Matthew J. Holland, Kazuki Tanabe

Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence, 2024

2023

A Survey of Learning Criteria Going Beyond the Usual Risk.

Matthew J. Holland, Kazuki Tanabe

J. Artif. Intell. Res., 2023

Implicit regularization via soft ascent-descent.

Matthew J. Holland, Kosuke Nakatani

CoRR, 2023

Flexible risk design using bi-directional dispersion.

Matthew J. Holland

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2023

2022

Learning with risks based on M-location.

Matthew J. Holland

Mach. Learn., 2022

Risk regularization through bidirectional dispersion.

Matthew J. Holland

CoRR, 2022

Spectral risk-based learning using unbounded losses.

Matthew J. Holland, El Mehdi Haress

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2022

Anytime Guarantees under Heavy-Tailed Data.

Matthew J. Holland

Proceedings of the Thirty-Sixth AAAI Conference on Artificial Intelligence, 2022

2021

Designing off-sample performance metrics.

Matthew J. Holland

CoRR, 2021

Robust learning with anytime-guaranteed feedback.

Matthew J. Holland

CoRR, 2021

Learning with risk-averse feedback under potentially heavy tails.

Matthew J. Holland, El Mehdi Haress

Proceedings of the 24th International Conference on Artificial Intelligence and Statistics, 2021

Scaling-Up Robust Gradient Descent Techniques.

Matthew J. Holland

Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence, 2021

2020

Better scalability under potentially heavy-tailed feedback.

Matthew J. Holland

CoRR, 2020

Non-monotone risk functions for learning.

Matthew J. Holland

CoRR, 2020

Making learning more transparent using conformalized performance prediction.

Matthew J. Holland

CoRR, 2020

Learning with CVaR-based feedback under potentially heavy tails.

Matthew J. Holland, El Mehdi Haress

CoRR, 2020

2019

Efficient learning with robust gradient descent.

Matthew J. Holland, Kazushi Ikeda

Mach. Learn., 2019

PAC-Bayes under potentially heavy tails.

Matthew J. Holland

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Better generalization with less data using robust gradient descent.

Matthew J. Holland, Kazushi Ikeda

Proceedings of the 36th International Conference on Machine Learning, 2019

Classification using margin pursuit.

Matthew J. Holland

Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics, 2019

Robust descent using smoothed multiplicative noise.

Matthew J. Holland

Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics, 2019

2017

Robust regression using biased objectives.

Matthew J. Holland, Kazushi Ikeda

Mach. Learn., 2017

2016

Minimum Proper Loss Estimators for Parametric Models.

Matthew J. Holland, Kazushi Ikeda

IEEE Trans. Signal Process., 2016

2015

Location robust estimation of predictive Weibull parameters in short-term wind speed forecasting.

Matthew J. Holland, Kazushi Ikeda

Proceedings of the 2015 IEEE International Conference on Acoustics, 2015

2014

Forecasting in wind energy applications with site-adaptive Weibull estimation.

Matthew J. Holland, Kazushi Ikeda

Proceedings of the IEEE International Conference on Acoustics, 2014