Publications

2025

• What is a Sketch-and-Precondition Derivation for Low-Rank Approximation? Inverse Power Error or Inverse Power Estimation?

  Ruihan Xu and Yiping Lu

  submitted.

• Physics-Informed Inference Time Scaling via Simulation-Calibrated Scientific Machine Learning

  Zexi Fan, Yan Sun, Shihao Yang and Yiping Lu

  submitted.

• RAGEN: Training Agents by Reinforcing Reasoning

  Zihan Wang, Kangrui Wang, Qineng Wang, Pingyue Zhang, Linjie Li, Zhengyuan Yang, Kefan Yu, Minh Nhat Nguyen, Licheng Liu, Eli Gottlieb, Monica Lam, Yiping Lu, Kyunghyun Cho, Jiajun Wu, Li Fei-Fei, Lijuan Wang, Yejin Choi and Manling Li

  submitted.

• A Simple Try Again Can Elicit Multi-Turn LLM Reasoning

  Licheng Liu, Zihan Wang, Linjie Li, Chenwei Xu, Yiping Lu, Han Liu, Avirup Sil and Manling Li

  submitted.

• Online Dynamic Mode Decomposition via First-Order Feedback

  Yuanlv Chen, Ruihan Xu and Yiping Lu

  submitted.

• Randomized Iterative Solver as Iterative Refinement: A Simple Fix Towards Backward Stability

  Ruihan Xu and Yiping Lu

  Artificial Intelligence and Statistics (AISTATS), 2025.

2024

• Bengin overfitting in Fixed Dimension via Physics-Informed Learning with Smooth Inductive Bias

  Honam Wong, Wendao Wu, Fanghui Liu and Yiping Lu

  submitted.

• Which Spaces can be Embedded in Lp-type Reproducing Kernel Banach Space? A Characterization via Metric Entropy

  Yiping Lu, Daozhe Lin and Qiang Du

  submitted.

• Orthogonal Bootstrap: Efficient Simulation of Input Uncertainty

  Kaizhao Liu, Jose Blanchet, Lexing Ying and Yiping Lu

  The Forty-first International Conference on Machine Learning (ICML 2024).

• Synthetic Principal Component Design: Fast Covariate Balancing with Synthetic Controls (Oral)

  Yiping Lu, Jiajin Li, Lexing Ying and Jose Blanchet

  40th Conference on Uncertainty in Artificial Intelligence (UAI 2024)

• Generalization Guarantees of Deep ResNets in the Mean-Field Regime (Spotlight)

  Yihang Chen, Fanghui Liu, Yiping Lu, Grigorios Chrysos and Volkan Cevher

  International Conference on Learning Representations(ICLR) 2024

• Statistical Spatially Inhomogeneous Diffusion Inference

  Yinuo Ren, Yiping Lu, Lexing Ying and Grant Rotskoff

  The 38th Annual AAAI Conference on Artificial Intelligence, 2024

Early Years

• When can Regression-Adjusted Control Variates Help? Rare Events, Sobolev Embedding and Minimax Optimality

  Jose Blanchet, Haoxuan Chen, Yiping Lu and Lexing Ying

  Thirty-seventh Conference on Neural Information Processing Systems (Neurips) 2023

• Minimax Optimal Kernel Operator Learning via Multilevel Training (Spotlight)

  Jikai Jin, Yiping Lu, Jose Blanchet, Lexing Ying

  Eleventh International Conference on Learning Representations(ICLR) 2023

• Adversarial Noises Are Linearly Separable for (Nearly) Random Neural Networks

  Huishuai Zhang, Da yu, Yiping Lu and Di He

  26th International Conference on Artificial Intelligence and Statistics (AISTATS) 2023

• Sobolev Acceleration and Statistical Optimality for Learning Elliptic Equations via Gradient Descent

  Yiping Lu, Jose Blanchet,Lexing Ying

  Thirty-sixth Conference on Neural Information Processing Systems (NeurIPS) 2022

• Machine Learning For Elliptic PDEs: Fast Rate Generalization Bound, Neural Scaling Law and Minimax Optimality (Spotlight Talk at NeurIPS 2021 Workshop on Integration of Deep Learning and Differential Equation)

  Yiping Lu, Haoxuan Chen, Jianfeng Lu, Lexing Ying, Jose Blanchet

  10th International Conference on Learning Representations(ICLR) 2022

• An Unconstrained Layer-Peeled Perspective on Neural Collapse

  Wenlong Ji, Yiping Lu, Yiliang Zhang, Zhun Deng, Weijie J Su

  Tenth International Conference on Learning Representations(ICLR) 2022

• CURE: Curvature Regularization For Missing Data Recovery

  Bin Dong, Haochen Ju, Yiping Lu, Zuoqiang Shi

  SIAM Journal on Imaging Science, 13(4), 2169-2188, 2020

• A Mean-field Analysis of Deep ResNet and Beyond: Towards Provable Optimization Via Overparameterization From Depth (Contributed Talk at ICLR 2020 Workshop on Integration of Deep Neural Models and Differential Equations.)

  Yiping Lu, Chao Ma, Yulong Lu, Jianfeng Lu, Lexing Ying

  Thirty-seventh International Conference on Machine Learning (ICML), 2020

• Understanding and Improving Transformer From a Multi-Particle Dynamic System Point of View

  Yiping Lu *, Zhuohan Li*, Di He, Zhiqing Sun, Bin Dong, Tao Qin, Liwei Wang, Tie-yan Liu

• You Only Propagate Once: Painless Adversarial Training Using Maximal Principle

  Dinghuai Zhang, Tianyuan Zhang, Yiping Lu, Zhanxing Zhu, Bin Dong

  33rd Annual Conference on Neural Information Processing Systems (NeurIPS) 2019

• PDE-Net 2.0: Learning PDEs from Data with A Numeric-Symbolic Hybrid Deep Network

  Zichao Long, Yiping Lu, Bin Dong

  Journal of Computational Physics

• Dynamically Unfolding Recurrent Restorer: A Moving Endpoint Control Method for Image Restoration

  Xiaoshuai Zhang*, Yiping Lu , Jiaying Liu, Bin Dong.

  Seventh International Conference on Learning Representations(ICLR) 2019

• PDE-Net:Learning PDEs From Data

  Zichao long*, Yiping Lu *, Xianzhong Ma*, Bin Dong

  Thirty-fifth International Conference on Machine Learning (ICML), 2018

• Beyond Finite Layer Neural Network:Bridging Deep Architects and Numerical Differential Equations

  Yiping Lu, Aoxiao Zhong, Quanzheng Li, Bin Dong.

  Thirty-fifth International Conference on Machine Learning (ICML), 2018