Runxin Xu

Adaptive Gradient Methods Can Be Provably Faster than SGD after Finite Epochs

2020 · arXiv (Cornell University)

Adaptive gradient methods have attracted much attention of machine learning communities due to the high efficiency. However their acceleration effect in practice, especially in neural network training, is hard to analyze, theoretically. The huge gap …

Double Graph Based Reasoning for Document-level Relation Extraction

2020

Document-level relation extraction aims to extract relations among entities within a document. Different from sentence-level relation extraction, it requires reasoning over multiple sentences across paragraphs. In this paper, we propose Graph Aggregation-and-Inference Network (GAIN), a …