arXiv subjects

Irwan Alnarus Kautsar

Publications and source records attributed to Irwan Alnarus Kautsar.

3 recordsLinked to original sources

arXiv2026

LLM-Guided Initialization for Accelerated Hybrid Quantum-Classical Medical Image Classification

Variational quantum algorithms often encounter barren plateaus, where cost gradients decay rapidly with increasing circuit depth, undermining the trainability of parameterized quantum circuits. This paper evaluates AdaInit (Adaptive Initialization), proposed by Zhuang and Cunningham, which uses large language models to propose initial parameters for quantum neural networks. We study a simplified single-query AdaInit variant paired with GPU-accelerated simulation in NVIDIA CUDA-Q and apply it to binary classification on the DMR-IR mammography dataset. AdaInit delivers 14.6 times higher gradient variance at initialization than random initialization (0.0095 vs. 0.0006), producing 160 times faster convergence (1.1s vs. 176 s) while maintaining the same classification accuracy of 61.4 percent. We provide theoretical analysis grounded in the geometry of parameterized circuit landscapes and show empirically that LLM-guided initialization places the optimizer in trainable regions of parameter space. Beyond performance, our results indicate that a single LLM query can yield informative parameters without iterative refinement, suggesting a low-overhead path to improved trainability. The findings validate AdaInit in a medical imaging setting and demonstrate its compatibility with GPU-accelerated quantum backends for practical speedups.

quant-ph↗

arXiv2026

Hybrid Quantum Neural Networks for Enhanced Breast Cancer Thermographic Classification: A Novel Quantum-Classical Integration Approach

Breast cancer diagnosis through thermographic image analysis remains a critical challenge in medical AI, with classical deep learning approaches facing limitations in complex thermal pattern classification tasks. This paper presents a novel Hybrid Quantum Neural Network (HQNN) architecture that integrates quantum computing principles with classical convolutional neural networks for enhanced breast cancer classification. Our approach employs parameterized quantum circuits with multi-head attention mechanisms for quantum-aware feature encoding, coupled with classical convolutional layers for comprehensive pattern recognition. The quantum component utilizes a 4qubit variational circuit with strongly entangling layers, while the classical component incorporates advanced attention mechanisms for feature fusion. Experimental validation on breast cancer thermographic data demonstrates substantial performance improvements over state-of-the-art classical architectures, with the quantum-enhanced approach exhibiting superior convergence dynamics and enhanced feature representation capabilities. Our findings provide evidence for quantum advantage in medical image classification through classical simulation, establishing a framework for quantum-classical hybrid systems in healthcare applications. The methodology addresses key challenges in quantum machine learning deployment while maintaining computational feasibility on near-term quantum devices.

quant-ph↗

arXiv2026

Accelerating Quantum State Encoding with SIMD: Design, Implementation, and Benchmarking

Efficient data encoding is the main factor affecting how fast hybrid quantum-classical algorithms run, but traditional simulators spend most of their time changing classical features into quantum rotations. This work introduces Hybriqu Encoder, a Rust-based, SIMD-aware kernel that focuses exclusively on angle encoding and integrates transparently with Python via CFFI. The kernel processes four double-precision rotations at once using AVX-class vector lanes, combines data in a way that fits well with the cache and uses pre-calculated trigonometric factors, while keeping all unsafe operations within a safe Rust interface. Benchmarks on Apple Silicon show that using pure angle encoding is 5.4% faster at 64 qubits, and the speedup increases as the amount of data exceeds the L1 cache size, while kernels that quickly apply rotations to the entire state vector are limited by memory and do not benefit from SIMD. These results indicate that using vectorization leads to consistent improvements when calculations are the main focus, but limits on data transfer speed prevent additional speed increases, highlighting the need for future efforts on better state updates and choosing between different processing methods. By combining smart optimization that considers the architecture with Rust's safety features, the Hybriqu Encoder offers a flexible base for bigger, mixed systems designed to reduce data encoding delays in future hybrid quantum-classical processes.

quant-ph↗