conftrace_

ensemble training

5 papers

Explore in graph

Co-occurring keywords

distributed training (188) gradient-based subset training (1) pre-training tax (1) neural network acoustic model (3) linear-predictive feature (1) out-of-distribution generalization (408) keyword spotting (145) gradient descent (1144) maximum entropy models (9) parameter mixtures (1)

Papers

PIEClass: Weakly-Supervised Text Classification with Prompting and Noise-Robust Iterative Ensemble Training EMNLP 2023

Lowering the Pre-training Tax for Gradient-based Subset Training: A Lightweight Distributed Pre-Training Toolkit ICML 2023

Evading the Simplicity Bias: Training a Diverse Set of Models Discovers Solutions With Superior OOD Generalization CVPR 2022

Improved Multilingual Training of Stacked Neural Network Acoustic Models for Low Resource Languages INTERSPEECH 2016

Efficient Large-Scale Distributed Training of Conditional Maximum Entropy Models NIPS 2009