A benchmark shows most time-series Transformers tolerate about 50% unstructured pruning without clear accuracy loss, while structured pruning rarely delivers meaningful inference speedups.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
A Comparative Study of Pruning Methods in Transformer-based Time Series Forecasting
A benchmark shows most time-series Transformers tolerate about 50% unstructured pruning without clear accuracy loss, while structured pruning rarely delivers meaningful inference speedups.