A Preliminary Investigation of Quantum-Assisted Ternary Weight Optimization for BitNet Neural Networks: Proof-of-Concept on Real IBM Quantum Hardware using a Hybrid Classical-Quantum Pipeline
Fuente:
Zenodo
Saved in:
| Main Author: | |
|---|---|
| Format: | Recurso digital |
| Language: | English |
| Published: |
Zenodo
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866902134563274752 |
|---|---|
| author | sh1vam, b |
| author_facet | sh1vam, b |
| contents | <p>We present a preliminary investigation of quantum-assisted training for BitNet neural networks, which constrain all weights to ternary values {-1, 0, +1} for memory efficiency. Classical gradient descent gets trapped in saddle points due to vanishing gradients through the sign() quantization function. We propose Quantum-Assisted Critical Weight Search (QACWS): gradient magnitude analysis identifies the 16 hardest weights for classical training; a QAOA-inspired quantum circuit on real IBM Torino hardware (133 qubits) searches exclusively those weights (1 qubit = 1 real weight); classical fine-tuning polishes the result. On a 16-bit XOR benchmark with a 272-weight BitNet model, the hybrid pipeline achieved 59.0% test accuracy, surpassing the classical plateau of 56.8% by +2.2 percentage points. We document a complete five-version experimental trajectory on IBM Torino quantum hardware revealing key failure modes and engineering solutions. All IBM Quantum job IDs are provided for full reproducibility. Source code: github.com/sh1vam-03/bitnet_quantum</p> |
| format | Recurso digital |
| id | zenodo_https___doi_org_10_5281_zenodo_19024106 |
| institution | Zenodo |
| language | eng |
| publishDate | 2026 |
| publisher | Zenodo |
| record_format | zenodo |
| spellingShingle | A Preliminary Investigation of Quantum-Assisted Ternary Weight Optimization for BitNet Neural Networks: Proof-of-Concept on Real IBM Quantum Hardware using a Hybrid Classical-Quantum Pipeline sh1vam, b BitNet quantum computing ternary neural networks IBM Quantum QAOA hybrid quantum-classical critical weight search 1-bit LLMs NISQ gradient magnitude analysis machine learning <p>We present a preliminary investigation of quantum-assisted training for BitNet neural networks, which constrain all weights to ternary values {-1, 0, +1} for memory efficiency. Classical gradient descent gets trapped in saddle points due to vanishing gradients through the sign() quantization function. We propose Quantum-Assisted Critical Weight Search (QACWS): gradient magnitude analysis identifies the 16 hardest weights for classical training; a QAOA-inspired quantum circuit on real IBM Torino hardware (133 qubits) searches exclusively those weights (1 qubit = 1 real weight); classical fine-tuning polishes the result. On a 16-bit XOR benchmark with a 272-weight BitNet model, the hybrid pipeline achieved 59.0% test accuracy, surpassing the classical plateau of 56.8% by +2.2 percentage points. We document a complete five-version experimental trajectory on IBM Torino quantum hardware revealing key failure modes and engineering solutions. All IBM Quantum job IDs are provided for full reproducibility. Source code: github.com/sh1vam-03/bitnet_quantum</p> |
| title | A Preliminary Investigation of Quantum-Assisted Ternary Weight Optimization for BitNet Neural Networks: Proof-of-Concept on Real IBM Quantum Hardware using a Hybrid Classical-Quantum Pipeline |
| topic | BitNet quantum computing ternary neural networks IBM Quantum QAOA hybrid quantum-classical critical weight search 1-bit LLMs NISQ gradient magnitude analysis machine learning |
| url | https://doi.org/10.5281/zenodo.19024106 |