Shuchin Aeron

Midway along a multi-pitch climb … “There is no choice …The only way out is up!” - Adam Young

Affiliations

Professor, Department of ECE, Tufts University 171 College Ave, Medford, MA 02464,
- Office: Halligan Hall, Room 144
Senior Investigator, NSF IAIFI
Secondary Appointments
- Tufts Department of Computer Science
- Tufts Department of Mathematics

Academic and Research Interests

Statistical Signal Processing
Tensor Factorization and Multilinear Algebra
Information Theory
High-Dimensional Statistics and Learning
- Optimal Transport, Generative Models
- Sparse Models for Signal Processing
- Contrastive Learning

Applications Areas

Inverse Problems for Remote/Sub-surface Sensing and Imaging (Geophysics, MRI, High-Energy Physics)
AI/ML for Learning and Cognitive Sciences: How students engage with confusion?
Bioinformatics

news

Sep 24, 2026	Paper “Primal-Dual Flow Matching for Sample-Wise Constrained Generation” accepted to NeuRIPS 2026
Sep 23, 2026	Paper “Inverse Problems Conditioned on Observation Ensembles: Applications and Methods” accepted to TMLR
Apr 28, 2026	Paper on Constrained Generation Accepted to TMLR
Oct 30, 2025	Paper on adversarial In-Context Learning (ICL) accepted to NeuRIPS 2025 main conference
Jan 27, 2025	Two papers on Optimal Transport accepted to AISTATS 2025 main conference

selected recent publications

generative modeling

Towards Universal Unfolding of Detector Effects in High-Energy Physics using Denoising Diffusion Probabilistic Models

Camila Pazos, Shuchin Aeron, Pierre-Hugues Beauchemin, Vincent Croft, Zhengyan Huan, Martin Klassen, and Taritree Wongjirad

Methods, 2024

Bib

@article{pazos2024towards,
  title = {Towards Universal Unfolding of Detector Effects in High-Energy Physics using Denoising Diffusion Probabilistic Models},
  author = {Pazos, Camila and Aeron, Shuchin and Beauchemin, Pierre-Hugues and Croft, Vincent and Huan, Zhengyan and Klassen, Martin and Wongjirad, Taritree},
  journal = {Methods},
  volume = {4},
  pages = {4},
  year = {2024}
}

contrastive learning

On Neural Collapse in Contrastive Learning with Imbalanced Datasets

Thuan Nguyen, Ruijie Jiang, Shuchin Aeron, Prakash Ishwar, and D. Richard Brown

In 2024 IEEE 34th International Workshop on Machine Learning for Signal Processing (MLSP), 2024

DOI Bib

@inproceedings{10734809,
  author = {Nguyen, Thuan and Jiang, Ruijie and Aeron, Shuchin and Ishwar, Prakash and Brown, D. Richard},
  booktitle = {2024 IEEE 34th International Workshop on Machine Learning for Signal Processing (MLSP)},
  title = {On Neural Collapse in Contrastive Learning with Imbalanced Datasets},
  year = {2024},
  volume = {},
  number = {},
  pages = {1-6},
  doi = {10.1109/MLSP58920.2024.10734809},
}

optimal transport

Linearized Wasserstein Barycenters: Synthesis, Analysis, Representational Capacity, and Applications

Matthew Werenski, Brendan Mallery, Shuchin Aeron, and James M. Murphy

2024

Bib

@misc{werenski2024linearizedwassersteinbarycenterssynthesis,
  title = {Linearized Wasserstein Barycenters: Synthesis, Analysis, Representational Capacity, and Applications},
  author = {Werenski, Matthew and Mallery, Brendan and Aeron, Shuchin and Murphy, James M.},
  year = {2024},
  eprint = {2410.23602},
  archiveprefix = {arXiv},
  primaryclass = {stat.ML},
  url = {https://arxiv.org/abs/2410.23602}
}

optimal transport

Synthesis and Analysis of Data as Probability Measures with Entropy-Regularized Optimal Transport

Brendan Mallery, James M. Murphy, and Shuchin Aeron

2025

Bib

@misc{mallery2025synthesisanalysisdataprobability,
  title = {Synthesis and Analysis of Data as Probability Measures with Entropy-Regularized Optimal Transport},
  author = {Mallery, Brendan and Murphy, James M. and Aeron, Shuchin},
  year = {2025},
  eprint = {2501.07446},
  archiveprefix = {arXiv},
  primaryclass = {stat.ML},
  url = {https://arxiv.org/abs/2501.07446}
}

optimal transport

Multivariate Soft Rank via Entropy-Regularized Optimal Transport: Sample Efficiency and Generative Modeling

Shoaib Bin Masud, Matthew Werenski, James M Murphy, and Shuchin Aeron

Journal of Machine Learning Research, 2023

Bib

@article{masud2023multivariate,
  title = {Multivariate Soft Rank via Entropy-Regularized Optimal Transport: Sample Efficiency and Generative Modeling},
  author = {Masud, Shoaib Bin and Werenski, Matthew and Murphy, James M and Aeron, Shuchin},
  journal = {Journal of Machine Learning Research},
  volume = {24},
  number = {160},
  pages = {1--65},
  year = {2023},
}

generative modeling

Score-based Diffusion Models for Generating Liquid Argon Time Projection Chamber Images

Zeviel Imani, Shuchin Aeron, and Taritree Wongjirad

Physical Review Letters D, 2024

Bib

@article{imani2023score,
  title = {Score-based Diffusion Models for Generating Liquid Argon Time Projection Chamber Images},
  author = {Imani, Zeviel and Aeron, Shuchin and Wongjirad, Taritree},
  journal = {Physical Review Letters D},
  year = {2024},
}

optimal transport

On Rank Energy Statistics via Optimal Transport: Continuity, Convergence, and Change Point Detection

Matthew Werenski, Shoaib Bin Masud, James M Murphy, and Shuchin Aeron

IEEE Transactions on Information Theory, 2024

Bib

@article{werenski2023rank,
  title = {On Rank Energy Statistics via Optimal Transport: Continuity, Convergence, and Change Point Detection},
  author = {Werenski, Matthew and Masud, Shoaib Bin and Murphy, James M and Aeron, Shuchin},
  journal = {IEEE Transactions on Information Theory},
  year = {2024},
  addendum = {preprint:arXiv preprint arXiv:2302.07964, Accepted, to Appear},
}