DDP replaces stochastic hard-concrete masks with a deterministic soft surrogate for l0-constrained structured pruning, delivering 1% performance loss on Qwen3 models at 20% sparsity and faster convergence than prior methods.
Prun- ing large language models with semi-structural adaptive sparse training.Proceedings of the AAAI Conference on Artificial Intelligence, 39(23):24167–24175, Apr
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Deterministic Differentiable Structured Pruning for Large Language Models
DDP replaces stochastic hard-concrete masks with a deterministic soft surrogate for l0-constrained structured pruning, delivering 1% performance loss on Qwen3 models at 20% sparsity and faster convergence than prior methods.