A new combinatorial measure, the domain shattering dimension, tightly controls, up to logarithmic factors, how many sampled domains are needed for domain generalization.
Metalearning with very few samples per task
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
How Many Domains Suffice for Domain Generalization? A Tight Characterization via the Domain Shattering Dimension
A new combinatorial measure, the domain shattering dimension, tightly controls, up to logarithmic factors, how many sampled domains are needed for domain generalization.