mlsanityData to 14 Oct 2026

One Qubit Can Beat One Bit: Quantum Advantage for Post-Training Quantization

arXiv 2608.05240 ↗First posted 5 Aug 2026quant-ph cs.AI cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

One-bit post-training quantization represents each weight using only its sign, requiring all deployment contexts to share the same binary weight matrix even when their activation statistics favor different sign patterns. We study this shared-sign constraint and introduce Quantum Random Access Quantization (QRAQ). This framework encodes context-dependent signs in a quantum random-access code and retrieves them via context-matched Pauli measurements. Under an explicit fresh-copy logical readout model, QRAQ produces an unbiased, context-specific binary surrogate with a tractable shot-noise penalty. We prove a row-wise separation from shared-sign one-bit PTQ with signed per-row scales. When the optimal context-wise signs are incompatible, QRAQ achieves a strictly lower ideal reconstruction risk. We also derive finite-shot and calibrated-noise conditions under which this separation is retained. Fixed-readout quantum schemes are classically simulable, so the relevant resource in this model is measurement incompatibility rather than quantization alone. Finally, we characterize the role of scale granularity, provide finite-sample certificates, and evaluate the predicted ideal, finite-shot, noisy, and multi-context regimes in simulator experiments.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 26 of its 40 references that are in the map. First posted on arXiv 5 Aug 2026.

Builds on

26 of 40 references.

References · 26

  1. 2024The Llama 3 Herd of Modelscited by 14,715
  2. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  3. 2022GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformerscited by 1,919
  4. 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,593
  5. 2023AWQ: Activation-aware Weight Quantization for LLM Compression and Accelerationcited by 1,298
  6. 2022LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scalecited by 906
  7. 2016XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networkscited by 849
  8. 2024QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMscited by 634
  9. 2019Learned Step Size Quantizationcited by 628
  10. 2023QuIP: 2-Bit Quantization of Large Language Models With Guaranteescited by 414
  11. 2024QuIP#: Even Better LLM Quantization with Hadamard Incoherence and Lattice Codebookscited by 378
  12. 2024The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bitscited by 308
14 more
  1. 2023BitNet: Scaling 1-bit Transformers for Large Language Modelscited by 189
  2. 2021Quantum advantage in learning from experimentscited by 188
  3. 2024BiLLM: Pushing the Limit of Post-Training Quantization for LLMscited by 144
  4. 2021Information-theoretic bounds on quantum advantage in machine learningcited by 96
  5. 2023PB-LLM: Partially Binarized Large Language Modelscited by 83
  6. 2024OneBit: Towards Extremely Low-bit Large Language Modelscited by 79
  7. 2017Extremely Low Bit Neural Network: Squeeze the Last Bit Out with ADMMcited by 61
  8. 2025GPTAQ: Efficient Finetuning-Free Quantization for Asymmetric Calibrationcited by 60
  9. 2025Quantization Error Propagation: Revisiting Layer-Wise Post-Training Quantizationcited by 41
  10. 2024A Survey of Low-bit Large Language Models: Basics, Systems, and Algorithmscited by 31
  11. 2024ARB-LLM: Alternating Refined Binarizations for Large Language Modelscited by 31
  12. 2025Qronos: Correcting the Past by Shaping the Future... in Post-Training Quantizationcited by 28
  13. 2025LoaQ: Layer-wise Output Approximation Quantizationcited by 5
  14. 2025Getting almost all the bits from a quantum random access codecited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Entanglement as Memory: Mechanistic Interpretability of Quantum Language Models
  2. 2026Circuit Hypernetworks for Quantum-Augmented Diffusion Language Models
  3. 2026Scale Sensitivity in Low-Bit Post-Training Quantization: Curvature of the Quantization Error Landscape
  4. 2026BCJR-QAT: A Differentiable Relaxation of Trellis-Coded Weight Quantization
  5. 2025ParetoQ: Improving Scaling Laws in Extremely Low-bit LLM Quantization
  6. 2026QART: A Quantum-Classical Hybrid Architecture for Long-Horizon Reasoning -- Exploring a Conditional Path toward Quantum Scaling
  7. 2026Saturation Makes Quantization Error Additive: A Coverage Model with a Certificate
  8. 2022On One-Bit Quantization