Matthew J. Holland
10 papers · 2019–2024 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+5 more ↓ Show less ↑
π§ Keyword Pioneer π Academic Marathon (5) π Cross-Pollinator (9) π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (21)
π
Conference Polyglot
(4)
πΊ
Lone Wolf
(7)
π
Keyword Champion
(3)
π
Century Club
(10)
ποΈ
Keyword Collector
(54)
Conferences
AISTATS (5)
AAAI (3)
ICML (1)
NIPS (1)
Top co-authors
Keywords
heavy-tailed distribution
(4)
heavy-tailed loss
(3)
risk minimization
(3)
gradient descent
(3)
loss function
(3)
loss distribution
(2)
robust gradient descent
(2)
stochastic optimization
(2)
online learning
(1)
finite sample analysis
(1)
risk management
(1)
distribution shift
(1)
excess risk
(1)
classification accuracy
(1)
learning theory
(1)
variance regularization
(1)
robust optimization
(1)
lipschitz continuity
(1)
excess risk bound
(1)
gradient aggregation
(1)
Papers
Soft ascent-descent as a stable and flexible alternative to flooding
NIPS 2024
A Survey of Learning Criteria Going beyond the Usual Risk (Abstract Reprint)
AAAI 2024
Robust variance-regularized risk minimization with concomitant scaling
AISTATS 2024
Criterion Collapse and Loss Distribution Control
ICML 2024
Flexible risk design using bi-directional dispersion
AISTATS 2023
Spectral risk-based learning using unbounded losses
AISTATS 2022
Anytime Guarantees under Heavy-Tailed Data
AAAI 2022
Scaling-Up Robust Gradient Descent Techniques
AAAI 2021
Robust descent using smoothed multiplicative noise
AISTATS 2019
Classification using margin pursuit
AISTATS 2019