Second Workshop on
Quantum Tensor Networks in Machine Learning

The workshop solicits the following submissions.

• Long paper (up to 9 pages, excluding references) describing original research work that has not been published before.
• Position paper (up to 6 pages, excluding references) reporting preliminary research findings or discussing inspiring and new directions.
• Extended abstract (up to 4 pages, excluding references) highlighting significant works that have been published.
• Poster advertising published works (conference or journal papers) or presenting new and unpublished solutions.

Formatting guidelines, LaTex styles and Word template:

• neurips_2021.tex -- LaTeX template
• neurips_2021.sty -- style file for LaTeX 2e
• poster template on overleaf -- choose any one you prefer

Submission site: https://cmt3.research.microsoft.com/QTNML2021

The reviewing process is double-blind. All submissions will be peer reviewed and evaluated based on technical contribution, originality, relevance to areas of interest, and presentation clarity. Papers may be accepted for either oral or poster presentation. We will also publish all the accepted papers and extended abstracts on the workshop website (with the authors' permission).

All submissions will be evaluated based on technical contribution, originality, relevance to areas of interest, and presentation clarity. Papers may be accepted for either oral or poster presentation.

This workshop is a non-archival venue and there will be no published proceedings. The accepted papers will be posted on the workshop website. It will be possible to submit the workshop submissions to other conferences and journals, if they accept such submissions.

This workshop aims to promote discussions among researchers investigating innovative QTNML technologies from perspectives of fundamental theory and algorithms, novel directions, and various applications in machine learning. Furthermore, researchers from multiple disciplines including machine learning, physics, and mathematics fields are encouraged to join the workshop to discuss the challenging problems and future research directions.

We are soliciting contributions that address a wide range of theoretical and practical issues including, but not limited to:

• Fundamental theory and algorithms for quantum tensor networks in machine learning
• Quantum machine learning algorithms via tensor networks
• Quantum advantages (speedups, learning efficiency, etc.) of quantum machine learning
• Quantum understanding of classical machine learning
• Quantum reinforcement learning via tensor networks
• Tensor networks for supervised, unsupervised and self-supervised quantum machine learning
• Tensor networks for dimensionality reduction and quantum-enhanced feature extraction
• Tensor networks for probabilistic/graphical modeling, generative models, quantum many-body systems
• Tensor network topological structure learning
• Tensor network layer for quantum machine learning algorithms
• Automatic differentiable programming for quantum tensor networks in machine learning
• Software development for tensor networks and quantum machine learning
• High performance quantum tensor networks on GPU(Tensor Cores)/FPGA/ASIC(TPU) platforms
• High performance classical simulation of quantum machine learning via tensor networks
• Applications of tensor networks and quantum machine learning