Hancheng Min

According to our database, Hancheng Min authored at least 28 papers between 2018 and 2026.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2026

On the Convergence, Implicit Bias, and Edge of Stability of Gradient Descent in Deep Learning: Reviewing recent progress [Special Issue on the Mathematics of Deep Learning].

Hancheng Min, Lachlan Ewen MacDonald, René Vidal

IEEE Signal Process. Mag., May, 2026

Transformers Learn the Optimal DDPM Denoiser for Multi-Token GMMs.

Hongkang Li, Hancheng Min, René Vidal

CoRR, April, 2026

2025

Voyaging into Unbounded Dynamic Scenes from a Single View.

Fengrui Tian, Tianjiao Ding, Jinqi Luo, Hancheng Min, René Vidal

CoRR, July, 2025

A Local Polyak-Łojasiewicz and Descent Lemma of Gradient Descent For Overparametrized Linear Models.

Ziqing Xu, Hancheng Min, Salma Tarmoun, Enrique Mallada, René Vidal

Trans. Mach. Learn. Res., 2025

A frequency domain analysis of slow coherency in networked systems.

Hancheng Min, Richard Pates, Enrique Mallada

Autom., 2025

Neural Collapse under Gradient Flow on Shallow ReLU Networks for Orthogonally Separable Data.

Hancheng Min, Zhihui Zhu, René Vidal

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2025, 2025

Convergence Rates for Gradient Descent on the Edge of Stability for Overparametrised Least Squares.

Lachlan E. MacDonald, Hancheng Min, Leandro Palma, Salma Tarmoun, Ziqing Xu, René Vidal

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2025, 2025

Gradient Flow Provably Learns Robust Classifiers for Orthonormal GMMs.

Hancheng Min, René Vidal

Proceedings of the Forty-second International Conference on Machine Learning, 2025

Voyaging into Perpetual Dynamic Scenes from a Single View.

Fengrui Tian, Tianjiao Ding, Jinqi Luo, Hancheng Min, René Vidal

Proceedings of the IEEE/CVF International Conference on Computer Vision, 2025

Concept Lancet: Image Editing with Compositional Representation Transplant.

Jinqi Luo, Tianjiao Ding, Kwan Ho Ryan Chan, Hancheng Min, Chris Callison-Burch, René Vidal

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2025

Understanding Incremental Learning with Closed-form Solution to Gradient Flow on Overparamerterized Matrix Factorization.

Hancheng Min, René Vidal

Proceedings of the 64th IEEE Conference on Decision and Control, 2025

Understanding the Learning Dynamics of LoRA: A Gradient Flow Perspective on Low-Rank Adaptation in Matrix Factorization.

Ziqing Xu, Hancheng Min, Lachlan Ewen MacDonald, Jinqi Luo, Salma Tarmoun, Enrique Mallada, René Vidal

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2025

2024

Oscillations-Aware Frequency Security Assessment via Efficient Worst-Case Frequency Nadir Computation.

Yan Jiang, Hancheng Min, Baosen Zhang

CoRR, 2024

Can Implicit Bias Imply Adversarial Robustness?

Hancheng Min, René Vidal

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Early Neuron Alignment in Two-layer ReLU Networks with Small Initialization.

Hancheng Min, Enrique Mallada, René Vidal

Proceedings of the Twelfth International Conference on Learning Representations, 2024

2023

Learning to Act Safely With Limited Exposure and Almost Sure Certainty.

Agustin Castellano, Hancheng Min, Juan Andrés Bazerque, Enrique Mallada

IEEE Trans. Autom. Control., May, 2023

Learning Coherent Clusters in Weakly-Connected Network Systems.

Hancheng Min, Enrique Mallada

Proceedings of the Learning for Dynamics and Control Conference, 2023

On the Convergence of Gradient Flow on Multi-layer Linear Models.

Hancheng Min, René Vidal, Enrique Mallada

Proceedings of the International Conference on Machine Learning, 2023

Spectral clustering and model reduction for weakly-connected coherent network systems.

Hancheng Min, Enrique Mallada

Proceedings of the American Control Conference, 2023

Linear Convergence of Gradient Descent For Finite Width Over-parametrized Linear Networks With General Initialization.

Ziqing Xu, Hancheng Min, Salma Tarmoun, Enrique Mallada, René Vidal

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2023

Learning Safety Critics via a Non-Contractive Binary Bellman Operator.

Agustin Castellano, Hancheng Min, Juan Andrés Bazerque, Enrique Mallada

Proceedings of the 57th Asilomar Conference on Signals, Systems, and Computers, ACSSC 2023, Pacific Grove, CA, USA, October 29, 2023

2022

Reinforcement Learning with Almost Sure Constraints.

Agustin Castellano, Hancheng Min, Enrique Mallada, Juan Andrés Bazerque

Proceedings of the Learning for Dynamics and Control Conference, 2022

2021

Coherence and Concentration in Tightly-Connected Networks.

Hancheng Min, Enrique Mallada

CoRR, 2021

On the Explicit Role of Initialization on the Convergence and Implicit Bias of Overparametrized Linear Networks.

Hancheng Min, Salma Tarmoun, René Vidal, Enrique Mallada

Proceedings of the 38th International Conference on Machine Learning, 2021

Accurate Reduced-Order Models for Heterogeneous Coherent Generators.

Hancheng Min, Fernando Paganini, Enrique Mallada

Proceedings of the 2021 American Control Conference, 2021

2019

Dynamics Concentration of Large-Scale Tightly-Connected Networks.

Hancheng Min, Enrique Mallada

Proceedings of the 58th IEEE Conference on Decision and Control, 2019

Accurate Reduced Order Models for Coherent Synchronous Generators.

Hancheng Min, Fernando Paganini, Enrique Mallada

Proceedings of the 57th Annual Allerton Conference on Communication, 2019

2018

Voronoi-Based Coverage Control of Pan/Tilt/Zoom Camera Networks.

Ömür Arslan, Hancheng Min, Daniel E. Koditschek

Proceedings of the 2018 IEEE International Conference on Robotics and Automation, 2018