Publications (41)
Computing the Proximal Operator of the -th Power of the -norm for Group Sparsity
Rongrong Lin, Shihai Chen, Han Feng +1
In this note, we comprehensively characterize the proximal operator of the -th power of the -norm (denoted by ) with by exploiting th…
Deeper Insights into Deep Graph Convolutional Networks: Stability and Generalization
Guangrui Yang, Ming Li, Han Feng +1
Graph convolutional networks (GCNs) have emerged as powerful models for graph learning tasks, exhibiting promising performance in various domains. While their empirical success is…
Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks
Luwei Sun, Dongrui Shen, Jianfe Li +2
Motivated by challenges in conditional generative modeling, where the target conditional density takes the form of a ratio f1 over f2, this paper develops a theoretical framework f…
HOPS: High-order Polynomials with Self-supervised Dimension Reduction for Load Forecasting
Pengyang Song, Han Feng, Shreyashi Shukla +2
Load forecasting is a fundamental task in smart grid. Many techniques have been applied to developing load forecasting models. Due to the challenges such as the Curse of Dimensiona…
First Application of Large Reactivity Measurement through Rod Drop Based on Three-Dimensional Space-Time Dynamics
Wencong Wang, Liyuan Huang, Caixue Liu +6
Reactivity measurement is an essential part of a zero-power physics test, which is critical to reactor design and development. The rod drop experimental technique is used to measur…
Escaping Locally Optimal Decentralized Control Polices via Damping
Han Feng, Javad Lavaei
We study the evolution of locally optimal decentralized controllers with the damping of the control system. Empirically it is shown that even for instances with an exponential numb…
Seedance 1.5 pro: A Native Audio-Visual Joint Generation Foundation Model
Team Seedance, Heyi Chen, Siyan Chen +194
Recent strides in video generation have paved the way for unified audio-visual generation. In this work, we present Seedance 1.5 pro, a foundational model engineered specifically f…
Spherical Image Inpainting with Frame Transformation and Data-driven Prior Deep Networks
Jianfei Li, Chaoyan Huang, Raymond Chan +3
Spherical image processing has been widely applied in many important fields, such as omnidirectional vision for autonomous cars, global climate modelling, and medical imaging. It i…
Mathematical Modeling of Business Reopening when Facing SARS-CoV-2 Pandemic: Protection, Cost and Risk
Hongyu Miao, Qianmiao Gao, Han Feng +11
The sudden onset of the coronavirus (SARS-CoV-2) pandemic has resulted in tremendous loss of human life and economy in more than 210 countries and territories around the world. Whi…
Gambling in contests with regret
Han Feng, David Hobson
This paper discusses the gambling contest introduced in Seel & Strack (Gambling in contests, Discussion Paper Series of SFB/TR 15 Governance and the Efficiency of Economic Systems…
Soul: Breathe Life into Digital Human for High-fidelity Long-term Multimodal Animation
Jiangning Zhang, Junwei Zhu, Zhenye Gan +14
We propose a multimodal-driven framework for high-fidelity long-term digital human animation termed , which generates semantically coherent videos from a single-fram…
StrandDesigner: Towards Practical Strand Generation with Sketch Guidance
Na Zhang, Moran Li, Chengming Xu +6
Realistic hair strand generation is crucial for applications like computer graphics and virtual reality. While diffusion models can generate hairstyles from text or images, these i…
Theory of Deep Convolutional Neural Networks II: Spherical Analysis
Zhiying Fang, Han Feng, Shuo Huang +1
Deep learning based on deep neural networks of various structures and architectures has been powerful in many practical applications, but it lacks enough theoretical verifications.…
Weighted Temporal Decay Loss for Learning Wearable PPG Data with Sparse Clinical Labels
Yunsung Chung, Keum San Chun, Migyeong Gwak +6
Advances in wearable computing and AI have increased interest in leveraging PPG for health monitoring over the past decade. One of the biggest challenges in developing health algor…
Convergence Analysis for Deep Sparse Coding via Convolutional Neural Networks
Jianfei Li, Han Feng, Ding-Xuan Zhou
In this work, we explore the intersection of sparse coding theory and deep learning to enhance our understanding of feature extraction capabilities in advanced neural network archi…
Identity-Preserving Text-to-Video Generation Guided by Simple yet Effective Spatial-Temporal Decoupled Representations
Yuji Wang, Moran Li, Xiaobin Hu +7
Identity-preserving text-to-video (IPT2V) generation, which aims to create high-fidelity videos with consistent human identity, has become crucial for downstream applications. Howe…
Chebyshev-type cubature formulas for doubling weights on spheres, balls and simplexes
Feng Dai, Han Feng
This paper proves that given a doubling weight on the unit sphere of , there exists a positive constant such that for each positive integ…
Permutation Equivariant Graph Framelets for Heterophilous Graph Learning
Jianfei Li, Ruigang Zheng, Han Feng +2
The nature of heterophilous graphs is significantly different from that of homophilous graphs, which causes difficulties in early graph neural network models and suggests aggregati…
Sparse-Aware Neural Networks for Nonlinear Functionals: Mitigating the Exponential Dependence on Dimension
Jianfei Li, Shuo Huang, Han Feng +2
Deep neural networks have emerged as powerful tools for learning operators defined over infinite-dimensional function spaces. However, existing theories frequently encounter diffic…
SignReLU neural network and its approximation ability
Jianfei Li, Han Feng, Ding-Xuan Zhou
Deep neural networks (DNNs) have garnered significant attention in various fields of science and technology in recent years. Activation functions define how neurons in DNNs process…
A Hitting Time Analysis for Stochastic Time-Varying Functions with Applications to Adversarial Attacks on Computation of Markov Decision Processes
Ali Yekkehkhany, Han Feng, Donghao Ying +1
Stochastic time-varying optimization is an integral part of learning in which the shape of the function changes over time in a non-deterministic manner. This paper considers multip…
Learning of Dynamical Systems under Adversarial Attacks -- Null Space Property Perspective
Han Feng, Baturalp Yalcin, Javad Lavaei
We study the identification of a linear time-invariant dynamical system affected by large-and-sparse disturbances modeling adversarial attacks or faults. Under the assumption that…
Isotropic Positive Definite Functions on Spheres
Han Feng, Yan Ge
In this paper, we investigate the relationship between positive definite functions on the unit sphere $\sph$ and on the Euclidean space $\RR^d$. For the dimension to be odd, a…
Approximation analysis of CNNs from a feature extraction view
Jianfei Li, Han Feng, Ding-Xuan Zhou
Deep learning based on deep neural networks has been very successful in many practical applications, but it lacks enough theoretical understanding due to the network architectures…
Stratified Avatar Generation from Sparse Observations
Han Feng, Wenchao Ma, Quankai Gao +3
Estimating 3D full-body avatars from AR/VR devices is essential for creating immersive experiences in AR/VR applications. This task is challenging due to the limited input from Hea…
Identifying Best Fair Intervention
Ruijiang Gao, Han Feng
We study the problem of best arm identification with a fairness constraint in a given causal model. The goal is to find a soft intervention on a given node to maximize the outcome…
Hypothesis Testing for Two Sample Comparison of Network Data
Han Feng, Xing Qiu, Hongyu Miao
Network data is a major object data type that has been widely collected or derived from common sources such as brain imaging. Such data contains numeric, topological, and geometric…
On the rates of convergence for learning with convolutional neural networks
Yunfei Yang, Han Feng, Ding-Xuan Zhou
We study approximation and learning capacities of convolutional neural networks (CNNs) with one-side zero-padding and multiple channels. Our first result proves a new approximation…
Spherical Analysis of Learning Nonlinear Functionals
Zhenyu Yang, Shuo Huang, Han Feng +1
In recent years, there has been growing interest in the field of functional neural networks. They have been proposed and studied with the aim of approximating continuous functional…
CRAFT: Clinical Reward-Aligned Finetuning for Medical Image Synthesis
Yunsung Chung, Alex El Darzi, Carlo El Khoury +3
Foundation diffusion models can generate photorealistic natural images, but adapting them to medical imaging remains challenging. In medical adaptation, limited labeled data can ex…
Radial Basis Function Approximation with Distributively Stored Data on Spheres
Han Feng, Shao-Bo Lin, Ding-Xuan Zhou
This paper proposes a distributed weighted regularized least squares algorithm (DWRLS) based on spherical radial basis functions and spherical quadrature rules to tackle spherical…
Uncertainty Principles on weighted spheres, balls and simplexes
Han Feng
This paper studies the uncertainty principle for spherical -harmonic expansions on the unit sphere of associated with a weight function invariant under a general…
Aggressive Local Search for Constrained Optimal Control Problems with Many Local Minima
Yuhao Ding, Han Feng, Javad Lavaei
This paper is concerned with numerically finding a global solution of constrained optimal control problems with many local minima. The focus is on the optimal decentralized control…
Convolutional Neural Networks for Spherical Signal Processing via Spherical Haar Tight Framelets
Jianfei Li, Han Feng, Xiaosheng Zhuang
In this paper, we develop a general theoretical framework for constructing Haar-type tight framelets on any compact set with a hierarchical partition. In particular, we construct a…
Reverse Hölder's inequality for spherical harmonics
Feng Dai, Han Feng, Sergey Tikhonov
This paper determines the sharp asymptotic order of the following reverse Hölder inequality for spherical harmonics of degree on the unit sphere of $\…
Theoretical Insights into CycleGAN: Analyzing Approximation and Estimation Errors in Unpaired Data Generation
Luwei Sun, Dongrui Shen, Han Feng
In this paper, we focus on analyzing the excess risk of the unpaired data generation model, called CycleGAN. Unlike classical GANs, CycleGAN not only transforms data between two un…
When and Why Naïve Diversification Works: A Simple Diagnostic Strategy
Han Feng, Difang Huang, Jue Wang +1
The paper identifies a simple condition—called the Golden Criterion—under which equal‑weight portfolios are minimum‑variance optimal, and proposes an adaptive two‑stage strategy th…
Fine-grained Analysis of Non-parametric Estimation for Pairwise Learning
Junyu Zhou, Shuo Huang, Han Feng +2
In this paper, we are concerned with the generalization performance of non-parametric estimation for pairwise learning. Most of the existing work requires the hypothesis space to b…
Bridging Smoothness and Approximation: Theoretical Insights into Over-Smoothing in Graph Neural Networks
Guangrui Yang, Jianfei Li, Ming Li +2
In this paper, we explore the approximation theory of functions defined on graphs. Our study builds upon the approximation results derived from the -functional. We establish a t…
Gambling in contests with random initial law
Han Feng, David Hobson
This paper studies a variant of the contest model introduced in Seel and Strack [J. Econom. Theory 148 (2013) 2033-2048]. In the Seel-Strack contest, each agent or contestant priva…
Best polynomial approximation on the triangle
Han Feng, Christian Krattenthaler, Yuan Xu
Let denote the error of best approximation by polynomials of degree at most in the space on the triangle $\{(x,y): x, y \ge 0, x+y…