Matthew J. Holland

Publication Activity (10 Years)

Years Active: 2014-2024
Publications (10 Years): 32

Top Topics

Risk Minimization

Multiplicative Noise

Robust Regression

Top Venues

Publications

Matthew J. Holland, Kazuki Tanabe
A Survey of Learning Criteria Going beyond the Usual Risk (Abstract Reprint). AAAI (2024)
Matthew J. Holland
Criterion collapse and loss distribution control. CoRR (2024)
Matthew J. Holland
Robust variance-regularized risk minimization with concomitant scaling. AISTATS (2024)
Matthew J. Holland, Kazuki Tanabe
A Survey of Learning Criteria Going Beyond the Usual Risk. J. Artif. Intell. Res. 78 (2023)
Matthew J. Holland, Kosuke Nakatani
Implicit regularization via soft ascent-descent. CoRR (2023)
Matthew J. Holland
Robust variance-regularized risk minimization with concomitant scaling. CoRR (2023)
Matthew J. Holland
Flexible risk design using bi-directional dispersion. AISTATS (2023)
Matthew J. Holland, El Mehdi Haress
Spectral risk-based learning using unbounded losses. AISTATS (2022)
Matthew J. Holland
Learning with risks based on M-location. Mach. Learn. 111 (12) (2022)
Matthew J. Holland
Anytime Guarantees under Heavy-Tailed Data. AAAI (2022)
Matthew J. Holland
Risk regularization through bidirectional dispersion. CoRR (2022)
Matthew J. Holland
Designing off-sample performance metrics. CoRR (2021)
Matthew J. Holland
Robust learning with anytime-guaranteed feedback. CoRR (2021)
Matthew J. Holland, El Mehdi Haress
Spectral risk-based learning using unbounded losses. CoRR (2021)
Matthew J. Holland
Scaling-Up Robust Gradient Descent Techniques. AAAI (2021)
Matthew J. Holland, El Mehdi Haress
Learning with risk-averse feedback under potentially heavy tails. AISTATS (2021)
Matthew J. Holland
Non-monotone risk functions for learning. CoRR (2020)
Matthew J. Holland
Making learning more transparent using conformalized performance prediction. CoRR (2020)
Matthew J. Holland
Improved scalability under heavy tails, without strong convexity. CoRR (2020)
Matthew J. Holland, El Mehdi Haress
Learning with CVaR-based feedback under potentially heavy tails. CoRR (2020)
Matthew J. Holland
Better scalability under potentially heavy-tailed gradients. CoRR (2020)
Matthew J. Holland
Better scalability under potentially heavy-tailed feedback. CoRR (2020)
Matthew J. Holland, Kazushi Ikeda
Efficient learning with robust gradient descent. Mach. Learn. 108 (8-9) (2019)
Matthew J. Holland
Robust descent using smoothed multiplicative noise. AISTATS (2019)
Matthew J. Holland
PAC-Bayes under potentially heavy tails. NeurIPS (2019)
Matthew J. Holland
PAC-Bayes under potentially heavy tails. CoRR (2019)
Matthew J. Holland, Kazushi Ikeda
Better generalization with less data using robust gradient descent. ICML (2019)
Matthew J. Holland
Classification using margin pursuit. AISTATS (2019)
Matthew J. Holland
Classification using margin pursuit. CoRR (2018)
Matthew J. Holland
Robust descent using smoothed multiplicative noise. CoRR (2018)
Matthew J. Holland, Kazushi Ikeda
Robust regression using biased objectives. Mach. Learn. 106 (9-10) (2017)
Matthew J. Holland, Kazushi Ikeda
Minimum Proper Loss Estimators for Parametric Models. IEEE Trans. Signal Process. 64 (3) (2016)
Matthew J. Holland, Kazushi Ikeda
Location robust estimation of predictive Weibull parameters in short-term wind speed forecasting. ICASSP (2015)
Matthew J. Holland, Kazushi Ikeda
Forecasting in wind energy applications with site-adaptive Weibull estimation. ICASSP (2014)