Kaiwu-PyTorch-Plugin: Bridging Deep Learning and Photonic Quantum Computing for Energy-Based Models and Active Sample Selection

TL;DR

The paper presents Kaiwu-PyTorch-Plugin, a framework that integrates photonic quantum computing with deep learning to improve energy-based models and active sampling, achieving state-of-the-art results.

Contribution

It introduces a novel plugin that bridges quantum photonic hardware with PyTorch, enabling efficient quantum-classical hybrid models and training methods.

Findings

Achieves state-of-the-art performance on single-cell datasets.

Demonstrates effective quantum acceleration in Boltzmann sampling.

Validates the quantum-classical hybrid paradigm with empirical results.

Abstract

This paper introduces the Kaiwu-PyTorch-Plugin (KPP) to bridge Deep Learning and Photonic Quantum Computing across multiple dimensions. KPP integrates the Coherent Ising Machine into the PyTorch ecosystem, addressing classical inefficiencies in Energy-Based Models. The framework facilitates quantum integration in three key aspects: accelerating Boltzmann sampling, optimizing training data via Active Sampling, and constructing hybrid architectures like QBM-VAE and Q-Diffusion. Empirical results on single-cell and OpenWebText datasets demonstrate KPPs ability to achieve SOTA performance, validating a comprehensive quantum-classical paradigm.