QLEACE removes all quadratically available class information from a representation, reliably slows feedforward networks, but can inject higher-order information that lets stronger architectures learn faster.
The ConvNeXts exhibit backfiring, achieving lower mean MDLs on surgically quadratically erased data than on unerased data
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
method 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
method 1polarities
unclear 1representative citing papers
citing papers explorer
-
Slowing Learning by Erasing Simple Features
QLEACE removes all quadratically available class information from a representation, reliably slows feedforward networks, but can inject higher-order information that lets stronger architectures learn faster.