conftrace_

compute-efficient training

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

compute efficiency (2) data subset selection (2) gradient matching (1) recurrent neural network transducer (1) model training (1) gradient-based sampling (1) subset selection (1) gradient-based method (1) automatic speech recognition (1) speech recognition (1)

Papers

AUTOMATA: Gradient Based Data Subset Selection for Compute-Efficient Hyper-parameter Tuning NeurIPS 2022 Partitioned Gradient Matching-based Data Subset Selection for Compute-Efficient Robust ASR Training EMNLP 2022