With per-method hyperparameter tuning, 50x top-k and DGC sparsification improved PTB LSTM perplexity by up to 0.06 over the uncompressed baseline, while QSGD and stronger compression performed at or below baseline.
Guided source separation meets a strong ASR backend: Hitachi/Paderborn university joint investigation for dinner party ASR,
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
-
Efficient Distributed Training through Gradient Compression with Sparsification and Quantization Techniques
With per-method hyperparameter tuning, 50x top-k and DGC sparsification improved PTB LSTM perplexity by up to 0.06 over the uncompressed baseline, while QSGD and stronger compression performed at or below baseline.