paper-with-me

홈 › Papers

IQP Born Machines under Data-dependent and Agnostic Initialization Strategies

2026-03-15 · Sacha Lerch, Joseph Bowles, Ricard Puig, Erik Armengol, Zoë Holmes, Supanut Thanasilp arxiv

Quantum circuit Born machines based on instantaneous quantum polynomial-time (IQP) circuits are natural candidates for quantum generative modeling, both because of their probabilistic structure and because IQP sampling is provably classically hard in certain regimes. Recent proposals focus on training IQP-QCBMs using Maximum Mean Discrepancy (MMD) losses built from low-body Pauli-$Z$ correlators, but the effect of initialization on the resulting optimization landscape remains poorly understood. In this work, we address this by first proving that the MMD loss landscape suffers from barren plateaus for random full-angle-range initializations of IQP circuits. We then establish lower bounds on the loss variance for identity and an unbiased data-agnostic initialization. We then additionally consider a data-dependent initialization that is better aligned with the target distribution and, under suitable assumptions, yields provable gradients and generally converges quicker to a good minimum (as indicated by our training of circuits with 150 qubits on genomic data). Finally, as a by-product, the developed variance lower bound framework is applicable to a general class of non-linear losses, offering a broader toolset for analyzing warm-starts in quantum machine learning.

📄 PDF Abstract BibTeX arXiv:2603.14576

Code (0)

등록된 구현이 없습니다.

Tasks

Quantum Machine Learning

Similar Papers 제목 키워드 기반

A newborn embodied Turing test for view-invariant object recognition

2023-06-08 · Denizhan Pak, Donsuk Lee, Samantha M. W. Wood, Justin N. Wood

Recent progress in artificial intelligence has renewed interest in building machines that learn like animals. Almost all of the work comparing learning across biological and artificial systems comes from studies where an…

Deep Reinforcement LearningObject Recognition

Quick Learning Mechanism with Cross-Domain Adaptation for Intelligent Fault Diagnosis

2021-03-16 · Arun K. Sharma, Nishchal K. Verma

The fault diagnostic model trained for a laboratory case machine fails to perform well on the industrial machines running under variable operating conditions. For every new operating condition of such machines, a new dia…

DiagnosticDomain AdaptationFault Diagnosis

Quantum-Aided Meta-Learning for Bayesian Binary Neural Networks via Born Machines

2022-03-31 · Ivana Nikoloska, Osvaldo Simeone

Near-term noisy intermediate-scale quantum circuits can efficiently implement implicit probabilistic models in discrete spaces, supporting distributions that are practically infeasible to sample from using classical mean…

Meta-LearningVariational Inference

Conditional Born machine for Monte Carlo event generation

2022-05-16 · Oriel Kiss, Michele Grossi, Enrique Kajomovitz, Sofia Vallecorsa

Generative modeling is a promising task for near-term quantum devices, which can use the stochastic nature of quantum measurements as a random source. So called Born machines are purely quantum models and promise to gene…

Quantum Generative Modeling of Sequential Data with Trainable Token Embedding

2023-11-08 · Wanda Hou, Li Miao, Yi-Zhuang You

Generative models are a class of machine learning models that aim to learn the underlying probability distribution of data. Unlike discriminative models, generative models focus on capturing the data's inherent structure…