Hsin-Yuan Huang

Out-of-distribution generalization for learning quantum dynamics

2022 · arXiv (Cornell University)

Generalization bounds are a critical tool to assess the training data requirements of Quantum Machine Learning (QML). Recent work has established guarantees for in-distribution generalization of quantum neural networks (QNNs), where training and testing data …

Preparing random states and benchmarking with many-body quantum chaos

2021 · arXiv (Cornell University)

Producing quantum states at random has become increasingly important in modern quantum science, with applications both theoretical and practical. In particular, ensembles of such randomly-distributed, but pure, quantum states underly our understanding of complexity in …

FlowQA: Grasping Flow in History for Conversational Machine\n Comprehension

2018 · arXiv (Cornell University)

Conversational machine comprehension requires the understanding of the\nconversation history, such as previous question/answer pairs, the document\ncontext, and the current question. To enable traditional, single-turn models to\nencode the history comprehensively, we introduce Flow, a mechanism that …