A single differential-inclusion search over masks produces a whole family of pruned transformers at different sparsity levels from one pretrained model.
(2013) for instance), while Assumption 1 (d) is also mild including all Lipschitz continuous convex function over a compact set
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
-
Adaptive Pruning of Pretrained Transformer via Differential Inclusions
A single differential-inclusion search over masks produces a whole family of pruned transformers at different sparsity levels from one pretrained model.