Matthew J. Holland - My portal

Profile Information

Affiliation: Assistant Professor, The Institute of Scientific and Industrial Research, Osaka University

Degree: Ph.D(Nara Institute of Science and Technology)

Researcher number: 00810227
ORCID ID: https://orcid.org/0000-0002-6704-1769
J-GLOBAL ID: 201701008049737949
researchmap Member ID: B000281787

Research Interests

Awards

Jul, 2023

Expert Reviewer, Transactions on Machine Learning Research (TMLR)

Matthew J. Holland
Jul, 2022

Distinguished Presentation Award (NEURO2022), Japanese Neural Network Society

Matthew J. Holland
Sep, 2021

Young Researcher Award (JNNS2021), Japanese Neural Network Society

Matthew J. Holland
Nov, 2019

Award finalist (IBIS 2019), IEICE, Information-Based Induction Sciences and Machine Learning (IBISML) Technical Committee

Matthew J. Holland
Mar, 2018

NAIST Top Student Award (PhD Program), Foundation for NAIST

Matthew James Holland
Feb, 2017

Student Paper Award, IEEE Kansai Section

Matthew James Holland
Mar, 2015

NAIST Top Student Award (Master's Program), Foundation for NAIST

Matthew James Holland

Papers

A Survey of Learning Criteria Going Beyond the Usual Risk

Matthew J. Holland, Kazuki Tanabe

Journal of Artificial Intelligence Research, 78 781-821, Nov, 2023 Peer-reviewed
Implicit regularization via soft ascent-descent

Matthew J. Holland, Kosuke Nakatani

arXiv preprint, Oct, 2023
Flexible risk design using bi-directional dispersion

Matthew J. Holland

Proceedings of Machine Learning Research (AISTATS 2023), 206 1586-1623, Apr, 2023 Peer-reviewed
Robust variance-regularized risk minimization with concomitant scaling

Matthew J. Holland

arXiv preprint, Jan, 2023
Learning with risks based on M-location

Matthew J. Holland

Machine Learning, 111 4679-4718, Aug, 2022 Peer-reviewed
Spectral risk-based learning using unbounded losses

Matthew J. Holland, El Mehdi Haress

Proceedings of Machine Learning Research (AISTATS 2022), 151(1) 1871-1886, Mar, 2022 Peer-reviewed
Anytime Guarantees under Heavy-Tailed Data

Matthew J. Holland

Proceedings of the AAAI Conference on Artificial Intelligence (AAAI 2022), 36(6) 6918-6925, Feb, 2022 Peer-reviewed
Making learning more transparent using conformalized performance prediction

Matthew J. Holland

ICML 2021, Workshop on Distribution-Free Uncertainty Quantification, Jul, 2021 Peer-reviewed
Robustness and scalability under heavy tails, without strong convexity

Matthew J. Holland

Proceedings of Machine Learning Research (AISTATS 2021), 130(1), Apr, 2021 Peer-reviewed
Learning with risk-averse feedback under potentially heavy tails

Matthew J. Holland, El Mehdi Haress

Proceedings of Machine Learning Research (AISTATS 2021), 130(1), Apr, 2021 Peer-reviewed
Scaling-Up Robust Gradient Descent Techniques

Matthew J. Holland

Proceedings of the AAAI Conference on Artificial Intelligence (AAAI 2021)., 35(9) 7694-7701, Feb, 2021 Peer-reviewed
Better scalability under potentially heavy-tailed feedback

Matthew J. Holland

Archival version, Dec, 2020
PAC-Bayes under potentially heavy tails

Matthew J. Holland

Advances in Neural Information Processing Systems 32 (NeurIPS 2019), Dec, 2019 Peer-reviewed
Efficient learning with robust gradient descent

Matthew J. Holland, Kazushi Ikeda

Machine Learning, 108(8) 1523-1560, Sep, 2019 Peer-reviewed
Distribution-robust mean estimation via smoothed random perturbations

Matthew J. Holland

arXiv preprint, Jun, 2019
Better generalization with less data using robust gradient descent

Matthew J. Holland, Kazushi Ikeda

Proceedings of Machine Learning Research (ICML 2019), 97 2761-2770, Jun, 2019 Peer-reviewed
Robust descent using smoothed multiplicative noise

Matthew J. Holland

Proceedings of Machine Learning Research (AISTATS 2019), 89(1) 703-711, Apr, 2019 Peer-reviewed
Classification using margin pursuit

Matthew J. Holland

Proceedings of Machine Learning Research (AISTATS 2019), 89(1) 712-720, Apr, 2019 Peer-reviewed
Robust regression using biased objectives

Matthew J. Holland, Kazushi Ikeda

Machine Learning, 106(9-10) 1643-1679, Oct, 2017 Peer-reviewed
Minimum Proper Loss Estimators for Parametric Models

Matthew J. Holland, Kazushi Ikeda

IEEE Transactions on Signal Processing, 64(3) 704-713, Feb, 2016 Peer-reviewed

Misc.

5分で分かる!? 有名論文ナナメ読み：Duchi, J. et al. : Adaptive Subgradient Methods for Online Learning and Stochastic Optimization

Matthew J. Holland

IPSJ Magazine, 60(8) 780-781, Jul, 2019 Invited
Robust gradient descent via back-propagation: A Chainer-based tutorial

Matthew J. Holland

May, 2019

Works

bdd-flood: links between bi-directional dispersion and flooding

Matthew J. Holland

Oct, 2023 Software
bdd-mv: mean-variance minimization using bi-directional dispersion functions

Matthew J. Holland

Jan, 2023 Software
offgen: a visual "explainer" for off-sample generalization metrics

Matthew J. Holland

Jul, 2022 Software
bdd: bidirectional dispersion and risk function design

Matthew J. Holland

Mar, 2022 Software
anytime: robust learning anytime

Matthew J. Holland

May, 2021 Software
spectral: learning based on spectral risks

May, 2021 Software
mrisk: learning with risks based on M-location

Matthew J. Holland

Apr, 2021 Software
sgd-roboost: robust confidence boosting of SGD sub-processes

Matthew J. Holland

Dec, 2020 Software
1dim (Python): estimators using smoothed random perturbations

Matthew J. Holland

Jun, 2019 Software
rgd (Python): Robust gradient descent examples

Matthew J. Holland

May, 2019 Software
catcube (Python): for new margin-based learning algorithms

Matthew J. Holland

Apr, 2019 Software
dosha-mesh (Python): Processing JMA landslide risk data

Matthew J. Holland

Aug, 2018 Software

Research Projects

Novel learning algorithms through off-sample generalization metric design

Grant-in-Aid for Scientific Research (B), Japan Society for the Promotion of Science, Apr, 2022 - Mar, 2026

Matthew J. Holland
Machine learning with guarantees under diverse risk measures

PRESTO (Fundamental Technologies for Trustworthy AI), JST, Oct, 2021 - Mar, 2025

Matthew J. Holland
Designing new learning algorithms via novel feedback generation mechanisms

JNNS30 Commemorative Research Grant, Japanese Neural Network Society, Jan, 2022 - Dec, 2022

Matthew J. Holland
Learning with guarantees under more diverse notions of risk

ACT-X (Frontier of Mathematics and Information Science), JST, Nov, 2020 - Mar, 2022

Matthew J. Holland
Robust and efficient learning algorithms through control of margin distributions

Grant-in-Aid for Early-Career Scientists, Japan Society for Promotion of Science, Apr, 2019 - Mar, 2022

Matthew J. Holland
Stabilization and performance guarantees for machine learning methods via margin distribution control

Research grant, Kayamori Foundation for Information Science Advancement, Jan, 2019 - Dec, 2020

Matthew J. Holland
Robust and efficient learning algorithms through control of margin distributions

Grant-in-Aid for Research Activity start-up, Japan Society for the Promotion of Science, Aug, 2018 - Mar, 2019

Matthew James Holland
Safe AI is efficient AI: improved generalization via robust learning algorithms

ACT-I (Information and Future), Japan Science and Technology Agency, Oct, 2017 - Mar, 2019

Matthew James Holland
Analysis of automated loss-selecting algorithms and their extension to time-series data

Grant-in-Aid for JSPS Fellows, Japan Society for the Promotion of Science, Apr, 2016 - Dec, 2017

Matthew James Holland