⚛️ Quantum Learning Theory Zoo
A curated list of research papers and key references in quantum learning theory. Use keyword chips (multi-select) and the year filter to narrow results.

Zookeeper: Junseo Lee
Last updated: October 16, 2025, 01:36 UTC
Contact: harris.junseo(at)gmail.com (This list may not be fully exhaustive, but I do my best to keep it up to date. If you know of any missing papers, have suggestions, or would like to collaborate, please feel free to get in touch anytime!)
About this zoo

This page focuses on learning and testing algorithms for understanding quantum systems and does not cover (variational) quantum machine learning models (e.g., QCNNs, QGANs).

Within each year, papers are sorted alphabetically by title.

When both arXiv and published (journal or conference) versions exist, the most recent publication year is shown, and all paper links point to the arXiv version.

Conference talks without official proceedings (e.g., QIP, QTML) are not included in the venue list. For TQC, only papers that appeared in its proceedings track are reflected.

Keyword descriptions 🔍
  • State Learning: Covers quantum state tomography and related estimation problems.
  • Process Learning: Includes learning of quantum channels, unitaries, and circuits.
  • Agnostic Learning: Studies learning without assuming the data-generating process fits a specific quantum model.
  • Hamiltonian Learning: Focuses on learning unknown Hamiltonians, including algorithms for quantum many-body systems.
  • PAC Learning: Explores Probably Approximately Correct (PAC) frameworks adapted to quantum settings.
  • Boolean Function: Relates to quantum learning of Boolean functions and Fourier analysis on the Boolean cube.
  • Property Testing: Concerns testing global properties of quantum states or processes.
  • Certification: Addresses verification and certification of quantum states, channels, or devices.
  • Continuous-Variable: Studies learning-theoretic problems in bosonic systems with infinite-dimensional Hilbert spaces.
  • Fermionic: Deals with learning problems involving fermionic quantum systems.
  • Pseudorandomness: Involves unitary designs, random unitaries, and pseudorandom quantum states related to quantum learning and lower bounds.
  • Survey: Includes review and overview papers summarizing progress in quantum learning theory.
Friends of this zoo 🐾

This project is inspired by other remarkable “zoo” collections in quantum information and theoretical computer science:

Useful resources on quantum learning theory 📚