Performance Evaluation of the Tensor Train Sampler in ML QUBO-Based ADMET Classification

Abstract

Quantum Annealing (QA) on D-Wave’s Advantage system and Tensor Train (TT) sampling are compared for QUBO-based ADMET classification. QA-based methods (QSVM, QBoost) leverage quantum effects to escape local minima, while TT sampling employs low-rank decompositions for efficient high-dimensional data handling. Benchmarks highlight TT sampling’s potential for improved optimization in drug discovery.

Cite

Text

Salloum et al. "Performance Evaluation of the Tensor Train Sampler in ML QUBO-Based ADMET Classification." ICLR 2025 Workshops: FPI, 2025.

Markdown

[Salloum et al. "Performance Evaluation of the Tensor Train Sampler in ML QUBO-Based ADMET Classification." ICLR 2025 Workshops: FPI, 2025.](https://mlanthology.org/iclrw/2025/salloum2025iclrw-performance/)

BibTeX

@inproceedings{salloum2025iclrw-performance,
  title     = {{Performance Evaluation of the Tensor Train Sampler in ML QUBO-Based ADMET Classification}},
  author    = {Salloum, Hadi and Sabbagh, Kamil and Lukin, Ruslan and Ryzhakov, Gleb and Kholodov, Yaroslav},
  booktitle = {ICLR 2025 Workshops: FPI},
  year      = {2025},
  url       = {https://mlanthology.org/iclrw/2025/salloum2025iclrw-performance/}
}