Оптимизация проксимальной точки Брегмана
method
ID: bregmanproximalpointoptimization
Related Papers
SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized Optimization
AbstractTransfer learning has fundamentally changed the landscape of natural language processing (NLP). Many state-of-the-art models are first pre-trained on a large text corpus and then fine-tuned on downstream tasks. However, …...