Publications

Preprints and submitted papers

Publications

• Optimal Regularization for a Data Source (with Eliza O'Reilly, Yong Sheng Soh, and Venkat Chandrasekaran)
  Foundations of Computational Mathematics 2024+. [arXiv]

• The Star Geometry of Critic-Based Regularizer Learning (with Eliza O'Reilly and Yong Sheng Soh)
  NeurIPS 2024. [arXiv]

• Flow Priors for Linear Inverse Problems via Iterative Corrupted Trajectory Matching (with Yasi Zhang, Peiyu Yu, Yaxuan Zhu, Yingshan Chang, Feng Gao, and Ying Nian Wu)
  NeurIPS 2024. [arXiv]

• Score-based Diffusion Models for Photoacoustic Tomography Image Reconstruction (with Sreemanti Dey, Snigdha Saha, Berthy T. Feng, Manxiu Cui, Laure Delisle, Lihong V. Wang, and Katherine L. Bouman)
  ICASSP 2024. [conference]

• Discovering Structure From Corruption for Unsupervised Image Reconstruction (with Angela Gao, He Sun, and Katie Bouman)
  IEEE Transactions on Computational Imaging 2023. [arXiv] [project page] [5-min video]

• Compressive Phase Retrieval: Optimal Sample Complexity with Deep Generative Priors (with Paul Hand and Vladislav Voroninski)
  Communications on Pure and Applied Mathematics 2024. [arXiv][journal]  

• Alternating Phase Langevin Sampling with Implicit Denoiser Priors for Phase Retrieval (with Rohun Agrawal*)
  ICASSP 2023. [arXiv]

• Image Reconstruction without Explicit Priors (with Angela Gao, He Sun, and Katie Bouman)
  ICASSP 2023. [arXiv]

• Optimal Sample Complexity of Subgradient Descent for Amplitude Flow via Non-Lipschitz Matrix Concentration (with Paul Hand and Vladislav Voroninski)
  Communications in Mathematical Sciences 2021. [arXiv] [journal]

• Invertible Generative Models for Inverse Problems: Mitigating Representation Error and Dataset Bias (with Muhammad Asim, Max Daniels, Ali Ahmed, and Paul Hand)
  ICML 2020. [arXiv]

• Optimally Sample-Efficient Phase Retrieval with Deep Generative Models (with Paul Hand and Vladislav Voroninski)
  SAMPTA 2019. Invited.

• Phase Retrieval Under a Generative Prior (with Paul Hand and Vladislav Voroninski)
  NeurIPS 2018. Oral Presentation (0.6% of submissions). [arXiv] 

• Proving Tucker's Lemma With a Volume Argument (with Beauttie Kuture, Christopher Loa, Mutiara Sondjaja, and Francis Su)
  Algebraic and Geometric Methods in Discrete Mathematics, 223-230, Contemp. Math., 685, Amer. Math. Soc., Providences, RI, 2017. [arXiv] 

Workshop papers

• Low Shot Learning with Untrained Neural Networks for Imaging Inverse Problems (with Wesam Sakla)
  NeurIPS 2019 Workshop on Solving Inverse Problems with Deep Networks. LatinX in AI Oral Presentation. [arXiv]