← Search

Mikhail Bragin

2 accepted papers

2023

Towards Lossless Head Pruning through Automatic Peer Distillation for Language Models

IJCAI 2023poster

Pruning has been extensively studied in Transformer-based language models to improve efficiency. Typically, we zero (prune) unimportant model weights and train a derived compact model to improve final accuracy. For pruned weights, we treat them as useless and discard them. This usually leads to sign…

Cited by 1SourcePDFScholar
2021

Enabling Retrain-free Deep Neural Network Pruning Using Surrogate Lagrangian Relaxation

IJCAI 2021poster

Network pruning is a widely used technique to reduce computation cost and model size for deep neural networks. However, the typical three-stage pipeline, i.e., training, pruning and retraining (fine-tuning) significantly increases the overall training trails. In this paper, we develop a systematic w…