A WiP paper claims a mathematical rationale for dynamically adjusting the KD loss balancing parameter, but the derivation only shows the loss-reduction size depends on the weighting.
Score-based generative modeling through stochastic differential equations
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Importance Analysis for Dynamic Control of Balancing Parameter in a Simple Knowledge Distillation Setting
A WiP paper claims a mathematical rationale for dynamically adjusting the KD loss balancing parameter, but the derivation only shows the loss-reduction size depends on the weighting.