publications | Wave Ngampruetikorn

Also available on Google Scholar and arXiv

* denotes equal contribution

2026

Preprint

Stochastic Resetting Accelerates Policy Convergence in Reinforcement Learning

Jello Zhou, Vudtiwat Ngampruetikorn^*, and David J Schwab^*

2026

Randomly resetting agents accelerates learning by truncating uninformative trajectories

arXiv Cite

@misc{zhou2026stochasticresettingacceleratespolicy,
  title = {Stochastic Resetting Accelerates Policy Convergence in Reinforcement Learning},
  author = {Zhou, Jello and Ngampruetikorn, Vudtiwat and Schwab, David J},
  year = {2026},
  eprint = {2603.16842},
  archiveprefix = {arXiv},
  primaryclass = {cs.LG},
  url = {https://arxiv.org/abs/2603.16842},
  summary = {Randomly resetting agents accelerates learning by truncating uninformative trajectories}
}

PRE

Data coarse graining can improve model performance

Alex Nguyen, David J Schwab^*, and Vudtiwat Ngampruetikorn^*

Physical Review E, 2026

Featured in Statistical Physics Meets Machine Learning - Machine Learning Meets Statistical Physics collection

Reducing data resolution can improve predictions by filtering low-relevance features

Paper Cite

@article{nguyen2026data,
  title = {Data coarse graining can improve model performance},
  author = {Nguyen, Alex and Schwab, David J and Ngampruetikorn, Vudtiwat},
  year = {2026},
  journal = {Physical Review E},
  doi = {10.1103/xn84-qzsw},
  volume = {113},
  issue = {2},
  pages = {025301},
  numpages = {8},
  _month = {Feb},
  publisher = {American Physical Society},
  url = {https://link.aps.org/doi/10.1103/xn84-qzsw},
  summary = {Reducing data resolution can improve predictions by filtering low-relevance features},
  note = {<b>Featured in <a href="https://journals.aps.org/pre/collections/ml-stat-pre">Statistical Physics Meets Machine Learning - Machine Learning Meets Statistical Physics</a> collection</b>}
}

2025

Preprint

Understanding temperature tuning in energy-based models

Peter W Fields, Vudtiwat Ngampruetikorn, David J Schwab, and Stephanie E Palmer

2025

arXiv Cite

@misc{fields2025understandingtemperaturetuningenergybased,
  title = {Understanding temperature tuning in energy-based models},
  author = {Fields, Peter W and Ngampruetikorn, Vudtiwat and Schwab, David J and Palmer, Stephanie E},
  year = {2025},
  eprint = {2512.09152},
  archiveprefix = {arXiv},
  primaryclass = {q-bio.QM},
  url = {https://arxiv.org/abs/2512.09152},
}

NeurIPS

Generalization vs Specialization under Concept Shift

Alex Nguyen, David J Schwab^*, and Vudtiwat Ngampruetikorn^*

In Advances in Neural Information Processing Systems, 2025

Distribution shift can drive phase transitions in model performance

OpenReview arXiv Cite

@inproceedings{nguyen2025generalization,
  title = {Generalization vs Specialization under Concept Shift},
  author = {Nguyen, Alex and Schwab, David J and Ngampruetikorn, Vudtiwat},
  booktitle = {Advances in Neural Information Processing Systems},
  year = {2025},
  url = {https://openreview.net/forum?id=kKPP6q5vBs},
  summary = {Distribution shift can drive phase transitions in model performance}
}

ICML

When can in-context learning generalize out of task distribution?

Chase Goddard, Lindsay M Smith, Vudtiwat Ngampruetikorn^*, and David J Schwab^*

In Forty-second International Conference on Machine Learning, 2025

Pretraining task diversity determines whether models generalize or specialize

OpenReview Cite

@inproceedings{goddard2025when,
  title = {When can in-context learning generalize out of task distribution?},
  author = {Goddard, Chase and Smith, Lindsay M and Ngampruetikorn, Vudtiwat and Schwab, David J},
  booktitle = {Forty-second International Conference on Machine Learning},
  year = {2025},
  url = {https://openreview.net/forum?id=YKyza9lrv4},
  summary = {Pretraining task diversity determines whether models generalize or specialize}
}

PRResearch

Extrinsic vs intrinsic criticality in systems with many components

Vudtiwat Ngampruetikorn, Ilya Nemenman^*, and David J Schwab^*

Physical Review Research, 2025

Apparent criticality in nature can emerge from hidden variables without fine-tuning

Paper Cite

@article{PhysRevResearch.7.013188,
  title = {Extrinsic vs intrinsic criticality in systems with many components},
  author = {Ngampruetikorn, Vudtiwat and Nemenman, Ilya and Schwab, David J},
  journal = {Physical Review Research},
  volume = {7},
  issue = {1},
  pages = {013188},
  numpages = {17},
  year = {2025},
  _month = {Feb},
  publisher = {American Physical Society},
  doi = {10.1103/PhysRevResearch.7.013188},
  url = {https://link.aps.org/doi/10.1103/PhysRevResearch.7.013188},
  summary = {Apparent criticality in nature can emerge from hidden variables without fine-tuning}
}

2024

PRL

Extreme Synergy in the Random-Energy Model

Vudtiwat Ngampruetikorn and David J Schwab

Physical Review Letters, 2024

Spin glasses naturally encode information like cryptographic secret-sharing schemes

Paper Cite

@article{PhysRevLett.133.257401,
  title = {Extreme Synergy in the Random-Energy Model},
  author = {Ngampruetikorn, Vudtiwat and Schwab, David J},
  journal = {Physical Review Letters},
  volume = {133},
  issue = {25},
  pages = {257401},
  numpages = {7},
  year = {2024},
  _month = {Dec},
  publisher = {American Physical Society},
  doi = {10.1103/PhysRevLett.133.257401},
  url = {https://link.aps.org/doi/10.1103/PhysRevLett.133.257401},
  summary = {Spin glasses naturally encode information like cryptographic secret-sharing schemes}
}

SciForDL @ NeurIPS

Specialization-generalization transition in exemplar-based in-context learning

Chase Goddard, Lindsay M Smith, Vudtiwat Ngampruetikorn, and David J Schwab

In NeurIPS 2024 Workshop on Scientific Methods for Understanding Deep Learning, 2024

Workshop version, see ICML 2025 for full paper

OpenReview Cite

@inproceedings{goddard2024specializationgeneralization,
  title = {Specialization-generalization transition in exemplar-based in-context learning},
  author = {Goddard, Chase and Smith, Lindsay M and Ngampruetikorn, Vudtiwat and Schwab, David J},
  booktitle = {NeurIPS 2024 Workshop on Scientific Methods for Understanding Deep Learning},
  year = {2024},
  url = {https://openreview.net/forum?id=D1ui5QwHqF},
  note = {Workshop version, see ICML 2025 for full paper}
}

SciForDL @ NeurIPS

Generalization vs Specialization under Concept Shift

Alex Nguyen, David J Schwab^*, and Vudtiwat Ngampruetikorn^*

In NeurIPS 2024 Workshop on Scientific Methods for Understanding Deep Learning, 2024

Workshop version, see NeurIPS 2025 for full paper

OpenReview Cite

@inproceedings{nguyen2024generalization,
  title = {Generalization vs Specialization under Concept Shift},
  author = {Nguyen, Alex and Schwab, David J and Ngampruetikorn, Vudtiwat},
  booktitle = {NeurIPS 2024 Workshop on Scientific Methods for Understanding Deep Learning},
  year = {2024},
  url = {https://openreview.net/forum?id=XcNJVw8iOB},
  note = {Workshop version, see NeurIPS 2025 for full paper}
}

SciForDL @ NeurIPS

Model Recycling: Model component reuse to promote in-context learning

Lindsay M Smith, Chase Goddard, Vudtiwat Ngampruetikorn^*, and David J Schwab^*

In NeurIPS 2024 Workshop on Scientific Methods for Understanding Deep Learning, 2024

OpenReview Cite

@inproceedings{smith2024model,
  title = {Model Recycling: Model component reuse to promote in-context learning},
  author = {Smith, Lindsay M and Goddard, Chase and Ngampruetikorn, Vudtiwat and Schwab, David J},
  booktitle = {NeurIPS 2024 Workshop on Scientific Methods for Understanding Deep Learning},
  year = {2024},
  url = {https://openreview.net/forum?id=vWSu8nEURM},
}

Front Phys

Anomalous Hall effects in chiral superconductors

Vudtiwat Ngampruetikorn and J A Sauls

Frontiers in Physics, 2024

Paper Cite

@article{10.3389/fphy.2024.1384275,
  author = {Ngampruetikorn, Vudtiwat and Sauls, J A},
  title = {Anomalous Hall effects in chiral superconductors},
  journal = {Frontiers in Physics},
  volume = {Volume 12 - 2024},
  year = {2024},
  url = {https://www.frontiersin.org/journals/physics/articles/10.3389/fphy.2024.1384275},
  doi = {10.3389/fphy.2024.1384275},
}

2023

Preprint

Generalized Information Bottleneck for Gaussian Variables

Vudtiwat Ngampruetikorn and David J Schwab

2023

arXiv Cite

@misc{ngampruetikorn2023generalizedinformationbottleneckgaussian,
  title = {Generalized Information Bottleneck for Gaussian Variables},
  author = {Ngampruetikorn, Vudtiwat and Schwab, David J},
  year = {2023},
  eprint = {2303.17762},
  archiveprefix = {arXiv},
  primaryclass = {cs.IT},
  url = {https://arxiv.org/abs/2303.17762},
}

SynS & ML @ ICML

Understanding Energy-Based Modeling of Proteins via an Empirically Motivated Minimal Ground Truth Model

Peter William Fields^*, Vudtiwat Ngampruetikorn^*, Rama Ranganathan, David J Schwab, and Stephanie Palmer

In ICML 2023 Workshop on the Synergy of Scientific and Machine Learning Modeling, 2023

OpenReview Cite

@inproceedings{fields2023understanding,
  title = {Understanding Energy-Based Modeling of Proteins via an Empirically Motivated Minimal Ground Truth Model},
  author = {Fields, Peter William and Ngampruetikorn, Vudtiwat and Ranganathan, Rama and Schwab, David J and Palmer, Stephanie},
  booktitle = {ICML 2023 Workshop on the Synergy of Scientific and Machine Learning Modeling},
  year = {2023},
  url = {https://openreview.net/forum?id=vxn5QGPFyi},
}

2022

NeurIPS

Information bottleneck theory of high-dimensional regression: relevancy, efficiency and optimality

Vudtiwat Ngampruetikorn and David J Schwab

In Advances in Neural Information Processing Systems, 2022

Spotlight presentation

Information-theoretic framework reveals the tradeoff between overfitting and learning

Paper Cite

@inproceedings{ngampruetikorn2022information,
  author = {Ngampruetikorn, Vudtiwat and Schwab, David J},
  booktitle = {Advances in Neural Information Processing Systems},
  editor = {Koyejo, S. and Mohamed, S. and Agarwal, A. and Belgrave, D. and Cho, K. and Oh, A.},
  pages = {9784--9796},
  publisher = {Curran Associates, Inc.},
  title = {Information bottleneck theory of high-dimensional regression: relevancy, efficiency and optimality},
  url = {https://proceedings.neurips.cc/paper_files/paper/2022/hash/3fbcfbc2b4009ae8dfa17a562532d123-Abstract-Conference.html},
  volume = {35},
  year = {2022},
  note = {<b>Spotlight presentation</b>},
  summary = {Information-theoretic framework reveals the tradeoff between overfitting and learning}
}

PRResearch

Inferring couplings in networks across order-disorder phase transitions

Vudtiwat Ngampruetikorn^*, Vedant Sachdeva^*, Johanna Torrence, Jan Humplik, David J Schwab, and Stephanie E Palmer

Physical Review Research, 2022

Network inference works best at intermediate temperatures between order and disorder

Cite

@article{ngampruetikorn2022inferring,
  title = {Inferring couplings in networks across order-disorder phase transitions},
  author = {Ngampruetikorn, Vudtiwat and Sachdeva, Vedant and Torrence, Johanna and Humplik, Jan and Schwab, David J and Palmer, Stephanie E},
  journal = {Physical Review Research},
  volume = {4},
  issue = {2},
  pages = {023240},
  numpages = {11},
  year = {2022},
  doi = {10.1103/PhysRevResearch.4.023240},
  summary = {Network inference works best at intermediate temperatures between order and disorder}
}

2021

NeurIPS

Perturbation Theory for the Information Bottleneck

Vudtiwat Ngampruetikorn and David J Schwab

In Advances in Neural Information Processing Systems, 2021

Derives analytical framework for learning onset in compressed representations

Paper Cite

@inproceedings{ngampruetikorn2021perturbation,
  author = {Ngampruetikorn, Vudtiwat and Schwab, David J},
  booktitle = {Advances in Neural Information Processing Systems},
  editor = {Ranzato, M. and Beygelzimer, A. and Dauphin, Y. and Liang, P.S. and Vaughan, J. Wortman},
  pages = {21008--21018},
  publisher = {Curran Associates, Inc.},
  title = {Perturbation Theory for the Information Bottleneck},
  url = {https://proceedings.neurips.cc/paper_files/paper/2021/hash/af8d9c4e238c63fb074b44eb6aed80ae-Abstract.html},
  volume = {34},
  year = {2021},
  summary = {Derives analytical framework for learning onset in compressed representations},
}

2020

ML4PS @ NeurIPS

Perturbation Theory for the Information Bottleneck

Vudtiwat Ngampruetikorn and David J Schwab

In NeurIPS 2020 Workshop on Machine Learning and the Physical Sciences, 2020

Workshop version, see NeurIPS 2021 for full paper

Paper Cite

@inproceedings{ngampruetikorn2020perturbation,
  title = {Perturbation Theory for the Information Bottleneck},
  author = {Ngampruetikorn, Vudtiwat and Schwab, David J},
  booktitle = {NeurIPS 2020 Workshop on Machine Learning and the Physical Sciences},
  year = {2020},
  url = {https://ml4physicalsciences.github.io/2020/files/NeurIPS_ML4PS_2020_136.pdf},
  note = {Workshop version, see NeurIPS 2021 for full paper}
}

PRL

Impurity-Induced Anomalous Thermal Hall Effect in Chiral Superconductors

Vudtiwat Ngampruetikorn and J A Sauls

Physical Review Letters, 2020

Impurities induce zero-field thermal Hall conductivity orders of magnitude larger than edge contributions

Cite

@article{ngampruetikorn2020impurity,
  title = {Impurity-Induced Anomalous Thermal Hall Effect in Chiral Superconductors},
  author = {Ngampruetikorn, Vudtiwat and Sauls, J A},
  journal = {Physical Review Letters},
  volume = {124},
  issue = {15},
  pages = {157002},
  year = {2020},
  doi = {10.1103/PhysRevLett.124.157002},
  summary = {Impurities induce zero-field thermal Hall conductivity orders of magnitude larger than edge contributions}
}

Nat Commun

Energy consumption and cooperation for optimal sensing

Vudtiwat Ngampruetikorn, David J Schwab^*, and Greg J Stephens^*

Nature Communications, 2020

Energy-consuming asymmetric couplings optimize cooperative sensing for noisy signals

Cite

@article{ngampruetikorn2020energy,
  title = {Energy consumption and cooperation for optimal sensing},
  author = {Ngampruetikorn, Vudtiwat and Schwab, David J and Stephens, Greg J},
  journal = {Nature Communications},
  volume = {11},
  pages = {975},
  year = {2020},
  doi = {10.1038/s41467-020-14806-y},
  summary = {Energy-consuming asymmetric couplings optimize cooperative sensing for noisy signals}
}

2019

PRResearch

Effect of inhomogeneous surface disorder on the superheating field of superconducting RF cavities

Vudtiwat Ngampruetikorn and J A Sauls

Physical Review Research, 2019

Cite

@article{ngampruetikorn2019effect,
  title = {Effect of inhomogeneous surface disorder on the superheating field of superconducting RF cavities},
  author = {Ngampruetikorn, Vudtiwat and Sauls, J A},
  journal = {Physical Review Research},
  volume = {1},
  issue = {1},
  pages = {012015(R)},
  year = {2019},
  doi = {10.1103/PhysRevResearch.1.012015},
}

2017

PLOS CB

Exploiting ecology in drug pulse sequences in favour of population reduction

Marianne Bauer, Isabella R Graf, Vudtiwat Ngampruetikorn, Greg J Stephens, and Erwin Frey

PLOS Computational Biology, 2017

Cite

@article{bauer2017exploiting,
  title = {Exploiting ecology in drug pulse sequences in favour of population reduction},
  author = {Bauer, Marianne and Graf, Isabella R and Ngampruetikorn, Vudtiwat and Stephens, Greg J and Frey, Erwin},
  journal = {PLOS Computational Biology},
  volume = {13},
  number = {9},
  pages = {e1005747},
  year = {2017},
  doi = {10.1371/journal.pcbi.1005747},
}

2016

PRE

Bias, belief, and consensus: Collective opinion formation on fluctuating networks

Vudtiwat Ngampruetikorn and Greg J Stephens

Physical Review E, 2016

Network dynamics and individual biases compete to shape consensus formation

Cite

@article{ngampruetikorn2016bias,
  title = {Bias, belief, and consensus: Collective opinion formation on fluctuating networks},
  author = {Ngampruetikorn, Vudtiwat and Stephens, Greg J},
  journal = {Physical Review E},
  volume = {94},
  issue = {5},
  pages = {052312},
  year = {2016},
  doi = {10.1103/PhysRevE.94.052312},
  summary = {Network dynamics and individual biases compete to shape consensus formation}
}

2015

PRA

High-temperature limit of the resonant Fermi gas

Vudtiwat Ngampruetikorn, Meera M Parish, and Jesper Levinsen

Physical Review A, 2015

Cite

@article{ngampruetikorn2015high,
  title = {High-temperature limit of the resonant Fermi gas},
  author = {Ngampruetikorn, Vudtiwat and Parish, Meera M and Levinsen, Jesper},
  journal = {Physical Review A},
  volume = {91},
  issue = {1},
  pages = {013606},
  numpages = {16},
  year = {2015},
  doi = {10.1103/PhysRevA.91.013606},
}

2013

PRL

Pair Correlations in the Two-Dimensional Fermi Gas

Vudtiwat Ngampruetikorn, Jesper Levinsen, and Meera M Parish

Physical Review Letters, 2013

Cite

@article{ngampruetikorn2013pair,
  title = {Pair Correlations in the Two-Dimensional Fermi Gas},
  author = {Ngampruetikorn, Vudtiwat and Levinsen, Jesper and Parish, Meera M},
  journal = {Physical Review Letters},
  volume = {111},
  issue = {26},
  pages = {265301},
  year = {2013},
  doi = {10.1103/PhysRevLett.111.265301},
}

EPL

Three-body problem in a two-dimensional Fermi gas

Vudtiwat Ngampruetikorn, Meera M Parish, and Jesper Levinsen

Europhysics Letters, 2013

Cite

@article{ngampruetikorn2013three,
  doi = {10.1209/0295-5075/102/13001},
  year = {2013},
  volume = {102},
  number = {1},
  pages = {13001},
  author = {Ngampruetikorn, Vudtiwat and Parish, Meera M and Levinsen, Jesper},
  title = {Three-body problem in a two-dimensional Fermi gas},
  journal = {Europhysics Letters},
}

2012

EPL

Repulsive polarons in two-dimensional Fermi gases

Vudtiwat Ngampruetikorn, Jesper Levinsen, and Meera M Parish

Europhysics Letters, 2012

Cite

@article{ngampruetikorn2012repulsive,
  doi = {10.1209/0295-5075/98/30005},
  year = {2012},
  volume = {98},
  number = {3},
  pages = {30005},
  author = {Ngampruetikorn, Vudtiwat and Levinsen, Jesper and Parish, Meera M},
  title = {Repulsive polarons in two-dimensional Fermi gases},
  journal = {Europhysics Letters},
}