Hongyi Zhang

Fast stochastic optimization on Riemannian manifolds.

2016 · arXiv (Cornell University)

We study optimization of finite sums of \emph{geodesically} smooth functions on Riemannian manifolds. Although variance reduction techniques for optimizing finite-sum problems have witnessed a huge surge of interest in recent years, all existing work is …

Posture Recognition Based on the Improved Optical Diffractive Neural Network

2020

Optical computing has significant advantages in power consumption efficiency and computing speed. As an optical machine learning framework, diffractive optical neural networks have achieved good results in the application of feature detection and target classification. …

End-to-End Federated Learning for Autonomous Driving Vehicles

2021

In recent years, with the development of computation capability in devices, companies are eager to investigate and utilize suitable ML/DL methods to improve their service quality. However, with the traditional learning strategy, companies need to …

Deep Reinforcement Learning for Multiple Agents in a Decentralized Architecture: A Case Study in the Telecommunication Domain

2023

Deep reinforcement learning has made significant development in recent years, and it is currently applied not only in simulators and games but also in embedded systems. However, when implemented in a real-world context, reinforcement learning …

Quantum switch for itinerant microwave single photons with superconducting quantum circuits

2024 · Physical Review Applied

A classical switch or router determines which of several inputs to the device passes through the output. In analogy, a quantum switch that coherently links the input to a superposition of several outputs plays an …

Lattice-Based Multi-Key Homomorphic Encryption Scheme Without Common Random Strings

2025 · Symmetry

Multi-key homomorphic encryption is widely applied into outsourced computing and privacy-preserving applications in multi-user scenarios. However, the existence of Common Random Strings (CRSs) weakens the ability of users to independently generate public keys, and it …

Scalable low-overhead superconducting nonlocal coupler for circuit connectivity enhancement

2026 · Physical Review Applied

Quantum error correction codes with non-local connections such as quantum low-density parity-check (qLDPC) incur lower overhead and outperform surface codes on large-scale devices. These codes are not applicable on current superconducting devices with nearest-neighbor connections. …