Matthew J. Holland
10 papers
· 2019–2024
· 4 conferences
· across top CS/AI conferences
Achievements
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
Flexible risk design using bi-directional dispersion
AISTATS 2023
Spectral risk-based learning using unbounded losses
AISTATS 2022
Robust descent using smoothed multiplicative noise
AISTATS 2019
Classification using margin pursuit
AISTATS 2019