Research
My research aims to develop rigorous foundations and algorithms for high-dimensional computational challenges in applied mathematics, statistics, and data science. These challenges are prevalent in fine-scale physical equations, large-scale machine learning datasets, and statistical/stochastic models with complex uncertainties. I use probability theory and numerical analysis with multiscale, randomized algorithms and recent progresses in machine learning to formalize and explore the following directions:
- How to understand and achieve provably efficient numerical estimation for PDEs, matrices, and probability distributions, especially in high dimensional or heterogeneous settings?
- How to accelerate and automate these estimations with machine learning rigorously?
Some specific topics are as follows:
- Multiscale analysis, randomized algorithms: numerical homogenization, randomized numerical linear algebra
- Gaussian processes, kernel methods: scalable algorithms, uncertainty quantification, learning theory
- Bayesian modeling, stochastic sampling: gradient flows, optimal transport, information geometry, diffusion models
In particular, my recent research focuses on the simulation, sampling, control, and statistical learning of high-dimensional probability distributions, with applications in scientific computing and machine learning. A core objective is to develop mathematical understanding of how dynamics of probability measures and their approximations behave in high-dimensional spaces, and how these insights can be used to systematically design probabilistic methods that automate and accelerate scientific applications. Applications I have been studying include imaging, molecular dynamics, chemistry, and forecasting.
Publications
Preprints
Stable Derivative Free Gaussian Mixture Variational Inference for Bayesian Inverse Problems Baojun Che, Yifan Chen, Zhenghao Huan, Daniel Zhengyu Huang, Weijie Wang Submitted. [arXiv] [Code]
Convergence of Unadjusted Langevin in High Dimensions: Delocalization of Bias Yifan Chen, Xiaoou Cheng, Jonathan Niles-Weed, Jonathan Weare Submitted. [arXiv] [Slide]
Fisher-Rao Gradient Flow: Geodesic Convexity and Functional Inequalities José A. Carrillo, Yifan Chen, Daniel Zhengyu Huang, Jiaoyang Huang, Dongyi Wei Submitted. [arXiv]
Sequential-in-time Training of Nonlinear Parametrizations for Solving Time-dependent Partial Differential Equations Huan Zhang, Yifan Chen, Eric Vanden-Eijnden, Benjamin Peherstorfer Submitted. [arXiv]
Sampling via Gradient Flows in the Space of Probability Measures Yifan Chen, Daniel Zhengyu Huang, Jiaoyang Huang, Sebastian Reich, Andrew M. Stuart Submitted. [arXiv] [Code] [Slide]
Conference Publications
Probabilistic Forecasting with Stochastic Interpolants and Follmer Processes Yifan Chen, Mark Goldstein, Mengjian Hua, Michael S. Albergo, Nicholas M. Boffi, Eric Vanden-Eijnden ICML, 2024. [Proceedings] [arXiv] [Slide] [Code] [Poster]
Inpainting crystal structure generations with score-based denoising Xinzhe Dai, Peichen Zhong, Bowen Deng, Yifan Chen, Gerbrand Ceder ICML Workshop AI4Science, 2024. [Proceedings]
Principled Probabilistic Imaging using Diffusion Models as Plug-and-Play Priors Zihui Wu, Yu Sun, Yifan Chen, Bingliang Zhang, Yisong Yue, Katherine L. Bouman NeurIPS, 2024. [Proceedings] [arXiv] [Code]
Journal Publications
Randomly Pivoted Cholesky: Practical Approximation of A Kernel Matrix with Few Entry Evaluations Yifan Chen, Ethan N. Epperly, Joel A. Tropp, Robert J. Webber Communications on Pure and Applied Mathematics, 2024. [Journal] [arXiv] [Code] [Slide]
Gaussian Measures Conditioned on Nonlinear Observations: Consistency, MAP Estimators, and Simulation Yifan Chen, Bamdad Hosseini, Houman Owhadi, Andrew M. Stuart Statistics and Computing, 2024. [Journal] [arXiv] [Code]
Efficient, Multimodal, and Derivative-Free Bayesian Inference with Fisher-Rao Gradient Flows Yifan Chen, Daniel Zhengyu Huang, Jiaoyang Huang, Sebastian Reich, Andrew M. Stuart Inverse Problems, 2024. [Journal] [arXiv] [Code] [Slide]
Error Analysis of Kernel/GP Methods for Nonlinear and Parametric PDEs Pau Batlle, Yifan Chen, Bamdad Hosseini, Houman Owhadi, Andrew M. Stuart Jounal of Computational Physics, 2024. [Journal] [arXiv] [Code]
Provable Probabilistic Imaging using Score-Based Generative Priors Yu Sun, Zihui Wu, Yifan Chen, Berthy T. Feng, Katherine L. Bouman IEEE Transactions on Computational Imaging, 2024. [Journal] [arXiv] [Code]
Sparse Cholesky Factorization for Solving Nonlinear PDEs via Gaussian Processes Yifan Chen, Houman Owhadi, Florian Schaefer Mathematics of Computation, 2024. [Journal] [arXiv] [Code] [Slide] [Slide+]
Exponentially Convergent Multiscale Methods for 2D High Frequency Heterogeneous Helmholtz Equations Yifan Chen, Thomas Y. Hou, Yixuan Wang SIAM Multiscale Modeling and Simulation, 2023. [Journal] [arXiv] [Slide] [Slide+]
Exponentially Convergent Multiscale Finite Element Method Yifan Chen, Thomas Y. Hou, Yixuan Wang Communications on Applied Mathematics and Computation, 2023. [Journal] [arXiv] [Slide] [Slide+]
Multiscale Elliptic PDEs Upscaling and Function Approximation via Subsampled Data Yifan Chen, Thomas Y. Hou SIAM Multiscale Modeling and Simulation, 2022. [Journal] [arXiv] [Code]
Solving and Learning Nonlinear PDEs with Gaussian Processes Yifan Chen, Bamdad Hosseini, Houman Owhadi, Andrew M. Stuart Jounal of Computational Physics, 2021. [Journal] [arXiv] [Code] [Slide] [Slide+]
Exponential Convergence for Multiscale Linear Elliptic PDEs via Adaptive Edge Basis Functions Yifan Chen, Thomas Y. Hou, Yixuan Wang SIAM Multiscale Modeling and Simulation, 2021. [Journal] [arXiv] [Slide] [Slide+]
Consistency of Empirical Bayes and Kernel Flow For Hierarchical Parameter Estimation Yifan Chen, Houman Owhadi, Andrew M. Stuart Mathematics of Computation, 2021. [Journal] [arXiv] [Code] [Slide] [Longer Slide] [Short Video] [Longer Video]
Function Approximation via The Subsampled Poincare Inequality Yifan Chen, Thomas Y. Hou Discrete & Continuous Dynamical Systems - A, 2020. [Journal] [arXiv]
Optimal Transport Natural Gradient for Statistical Manifolds with Continuous Sample Space Yifan Chen, Wuchen Li Information Geometry, 2020. [Journal] [arXiv] [Code] [Slide]
Run-and-Inspect Method for Nonconvex Optimization and Global Optimality Bounds for R-Local Minimizers Yifan Chen, Yuejiao Sun, Wotao Yin Mathematical Programming, 2019. [Journal] [arXiv] [Slide]
The Quadratic Wasserstein Metric for Earthquake Location Jing Chen, Yifan Chen, Hao Wu, Dinghui Yang Journal of Computational Physics, 2018. [Journal] [arXiv] [Slide]
Thesis
On Multiscale and Statistical Numerical Methods for PDEs and Inverse Problems Yifan Chen Ph.D. Thesis, The W.P. Carey and Co. Prize in Applied Mathematics, 2023 [CaltechTHESIS] [Slide]
Notes
Gradient Flows for Sampling: Mean-Field Models, Gaussian Approximations and Affine Invariance Yifan Chen, Daniel Zhengyu Huang, Jiaoyang Huang, Sebastian Reich, Andrew M. Stuart [arXiv]
Professional Experience
Referee Service
- Reviewer for NeurIPS 2024
- Reviewer for Journal of Functional Analysis
- Reviewer for Mathematics of Computation
- Reviewer for Journal of Computational Physics
- Reviewer for SIAM on Uncertainty Quantification
- Reviewer for SIAM on Mathematics of Data Science
- Reviewer for SIAM on Multiscale Modeling and Simulation
- Reviewer for SIAM on Numerical Analysis
- Reviewer for SIAM on Control and Optimization
- Reviewer for IMA Journal of Numerical Analysis
- Reviewer for Linear Algebra and Its Applications
- Reviewer for Nature Machine Intelligence
- Reviewer for European Journal of Applied Mathematics
- Reviewer for Foundations of Data Science
- Reviewer for Discrete and Continuous Dynamical Systems
- Reviewer for Research in the Mathematical Sciences
- Reviewer for Computational Methods in Applied Mathematics
- Reviewer for International Journal of Computer Mathematics
- Reviewer for 4th International Conference, GSI 2019