Bei Jiang

Towards Understanding Distributional Reinforcement Learning: Regularization, Optimization, Acceleration and Sinkhorn Algorithm.

2021 · arXiv (Cornell University)

Distributional reinforcement learning~(RL) is a class of state-of-the-art algorithms that estimate the whole distribution of the total return rather than only its expectation. Despite the remarkable performance of distributional RL, a theoretical understanding of its …

Word Embeddings via Causal Inference: Gender Bias Reducing and Semantic\n Information Preserving

2021 · arXiv (Cornell University)

With widening deployments of natural language processing (NLP) in daily life,\ninherited social biases from NLP models have become more severe and\nproblematic. Previous studies have shown that word embeddings trained on\nhuman-generated corpora have strong gender biases …