Paper
Quantum Maximum Likelihood Prediction via Hilbert Space Embeddings
Authors
Sreejith Sreekumar, Nir Weinberger
Abstract
Recent works have proposed various explanations for the ability of modern large language models (LLMs) to perform in-context prediction. We propose an alternative conceptual viewpoint from an information-geometric and statistical perspective. Motivated by Bach[2023], we model training as learning an embedding of probability distributions into the space of quantum density operators, and in-context learning as maximum-likelihood prediction over a specified class of quantum models. We provide an interpretation of this predictor in terms of quantum reverse information projection and quantum Pythagorean theorem when the class of quantum models is sufficiently expressive. We further derive non-asymptotic performance guarantees in terms of convergence rates and concentration inequalities, both in trace norm and quantum relative entropy. Our approach provides a unified framework to handle both classical and quantum LLMs.
Metadata
Related papers
Vibe Coding XR: Accelerating AI + XR Prototyping with XR Blocks and Gemini
Ruofei Du, Benjamin Hersh, David Li, Nels Numan, Xun Qian, Yanhe Chen, Zhongy... • 2026-03-25
Comparing Developer and LLM Biases in Code Evaluation
Aditya Mittal, Ryan Shar, Zichu Wu, Shyam Agarwal, Tongshuang Wu, Chris Donah... • 2026-03-25
The Stochastic Gap: A Markovian Framework for Pre-Deployment Reliability and Oversight-Cost Auditing in Agentic Artificial Intelligence
Biplab Pal, Santanu Bhattacharya • 2026-03-25
Retrieval Improvements Do Not Guarantee Better Answers: A Study of RAG for AI Policy QA
Saahil Mathur, Ryan David Rittner, Vedant Ajit Thakur, Daniel Stuart Schiff, ... • 2026-03-25
MARCH: Multi-Agent Reinforced Self-Check for LLM Hallucination
Zhuo Li, Yupeng Zhang, Pengyu Cheng, Jiajun Song, Mengyu Zhou, Hao Li, Shujie... • 2026-03-25
Raw Data (Debug)
{
"raw_xml": "<entry>\n <id>http://arxiv.org/abs/2602.18364v1</id>\n <title>Quantum Maximum Likelihood Prediction via Hilbert Space Embeddings</title>\n <updated>2026-02-20T17:16:38Z</updated>\n <link href='https://arxiv.org/abs/2602.18364v1' rel='alternate' type='text/html'/>\n <link href='https://arxiv.org/pdf/2602.18364v1' rel='related' title='pdf' type='application/pdf'/>\n <summary>Recent works have proposed various explanations for the ability of modern large language models (LLMs) to perform in-context prediction. We propose an alternative conceptual viewpoint from an information-geometric and statistical perspective. Motivated by Bach[2023], we model training as learning an embedding of probability distributions into the space of quantum density operators, and in-context learning as maximum-likelihood prediction over a specified class of quantum models. We provide an interpretation of this predictor in terms of quantum reverse information projection and quantum Pythagorean theorem when the class of quantum models is sufficiently expressive. We further derive non-asymptotic performance guarantees in terms of convergence rates and concentration inequalities, both in trace norm and quantum relative entropy. Our approach provides a unified framework to handle both classical and quantum LLMs.</summary>\n <category scheme='http://arxiv.org/schemas/atom' term='cs.IT'/>\n <category scheme='http://arxiv.org/schemas/atom' term='cs.LG'/>\n <category scheme='http://arxiv.org/schemas/atom' term='quant-ph'/>\n <category scheme='http://arxiv.org/schemas/atom' term='stat.ML'/>\n <published>2026-02-20T17:16:38Z</published>\n <arxiv:comment>32+4 pages, 1 figure</arxiv:comment>\n <arxiv:primary_category term='cs.IT'/>\n <author>\n <name>Sreejith Sreekumar</name>\n </author>\n <author>\n <name>Nir Weinberger</name>\n </author>\n </entry>"
}