Fanghui Liu

Orcid: 0000-0003-4133-7921

Affiliations:
  • University of Warwick, Department of Computer Science, UK
  • École Polytechnique Fédérale de Lausanne (EPFL), Switzerland (former)
  • KU Leuven, Belgium (former)
  • Shanghai Jiao Tong University, China (former)


According to our database1, Fanghui Liu authored at least 67 papers between 2015 and 2024.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

Online presence:

On csauthors.net:

Bibliography

2024
Learning with Norm Constrained, Over-parameterized, Two-layer Neural Networks.
J. Mach. Learn. Res., 2024

Benign overfitting in Fixed Dimension via Physics-Informed Learning with Smooth Inductive Bias.
CoRR, 2024

Revisiting character-level adversarial attacks.
CoRR, 2024

Can overfitted deep neural networks in adversarial training generalize? - An approximation viewpoint.
CoRR, 2024

High-Dimensional Kernel Methods under Covariate Shift: Data-Dependent Implicit Regularization.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

Revisiting Character-level Adversarial Attacks for Language Models.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

Robust NAS under adversarial training: benchmark, theory, and beyond.
Proceedings of the Twelfth International Conference on Learning Representations, 2024

Generalization of Scaled Deep ResNets in the Mean-Field Regime.
Proceedings of the Twelfth International Conference on Learning Representations, 2024

Efficient local linearity regularization to overcome catastrophic overfitting.
Proceedings of the Twelfth International Conference on Learning Representations, 2024

Learning Scalable Model Soup on a Single GPU: An Efficient Subspace Training Strategy.
Proceedings of the Computer Vision - ECCV 2024, 2024

The Role of Over-Parameterization in Machine Learning - the Good, the Bad, the Ugly.
Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence, 2024

2023
Federated Learning under Covariate Shifts with Generalization Guarantees.
Trans. Mach. Learn. Res., 2023

End-to-end kernel learning via generative random Fourier features.
Pattern Recognit., 2023

Provable benefits of general coverage conditions in efficient online RL with function approximation.
CoRR, 2023

On the Convergence of Encoder-only Shallow Transformers.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Initialization Matters: Privacy-Utility Analysis of Overparameterized Neural Networks.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Benign Overfitting in Deep Neural Networks under Lazy Training.
Proceedings of the International Conference on Machine Learning, 2023

What can online reinforcement learning with function approximation benefit from general coverage conditions?
Proceedings of the International Conference on Machine Learning, 2023

2022
Towards a Unified Quadrature Framework for Large-Scale Kernel Machines.
IEEE Trans. Pattern Anal. Mach. Intell., 2022

Random Features for Kernel Approximation: A Survey on Algorithms, Theory, and Beyond.
IEEE Trans. Pattern Anal. Mach. Intell., 2022

Random Fourier Features for Asymmetric Kernels.
CoRR, 2022

Understanding Deep Neural Function Approximation in Reinforcement Learning via ε-Greedy Exploration.
CoRR, 2022

Robustness in deep learning: The good (width), the bad (depth), and the ugly (initialization).
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Generalization Properties of NAS under Activation and Skip Connection Search.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Extrapolation and Spectral Bias of Neural Nets with Hadamard Product: a Polynomial Net Study.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Sound and Complete Verification of Polynomial Networks.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Understanding Deep Neural Function Approximation in Reinforcement Learning via $\epsilon$-Greedy Exploration.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

On the Double Descent of Random Features Models Trained with SGD.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

2021
Analysis of regularized least-squares in reproducing kernel Kreĭn spaces.
Mach. Learn., 2021

Generalization Properties of hyper-RKHS and its Applications.
J. Mach. Learn. Res., 2021

Kernel regression in high dimensions: Refined analysis beyond double descent.
Proceedings of the 24th International Conference on Artificial Intelligence and Statistics, 2021

Fast Learning in Reproducing Kernel Krein Spaces via Signed Measures.
Proceedings of the 24th International Conference on Artificial Intelligence and Statistics, 2021

2020
A Double-Variational Bayesian Framework in Random Fourier Features for Indefinite Kernels.
IEEE Trans. Neural Networks Learn. Syst., 2020

Learning Data-adaptive Non-parametric Kernels.
J. Mach. Learn. Res., 2020

Kernel regression in high dimension: Refined analysis beyond double descent.
CoRR, 2020

Analysis of Least Squares Regularized Regression in Reproducing Kernel Krein Spaces.
CoRR, 2020

Generalizing Random Fourier Features via Generalized Measures.
CoRR, 2020

Random Fourier Features via Fast Surrogate Leverage Weighted Sampling.
Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence, 2020

2019
Indefinite Kernel Logistic Regression With Concave-Inexact-Convex Procedure.
IEEE Trans. Neural Networks Learn. Syst., 2019

Deep Kernel Learning via Random Fourier Features.
CoRR, 2019

Sparse Indefinite Kernel Learning on Sphere.
Aust. J. Intell. Inf. Process. Syst., 2019

Dense Multi-focus Fusion Net: A Deep Unsupervised Convolutional Network for Multi-focus Image Fusion.
Proceedings of the Artificial Intelligence and Soft Computing, 2019

2018
Robust Visual Tracking Revisited: From Correlation Filter to Template Matching.
IEEE Trans. Image Process., 2018

Robust Visual Tracking via Online Discriminative and Low-Rank Dictionary Learning.
IEEE Trans. Cybern., 2018

Inverse Nonnegative Local Coordinate Factorization for Visual Tracking.
IEEE Trans. Circuits Syst. Video Technol., 2018

Robust Visual Tracking via Dirac-Weighted Cascading Correlation Filters.
IEEE Signal Process. Lett., 2018

Densely Connected Discriminative Correlation Filters for Visual Tracking.
IEEE Signal Process. Lett., 2018

Online discriminative dictionary learning for robust object tracking.
Neurocomputing, 2018

Generalization Properties of hyper-RKHS and its Application to Out-of-Sample Extensions.
CoRR, 2018

Learning Data-adaptive Nonparametric Kernels.
CoRR, 2018

Deep-PUMR: Deep Positive and Unlabeled Learning with Manifold Regularization.
Proceedings of the Neural Information Processing - 25th International Conference, 2018

Nonlinear Pairwise Layer and Its Training for Kernel Learning.
Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, 2018

2017
Visual Tracking via Nonnegative Multiple Coding.
IEEE Trans. Multim., 2017

Graph Regularized and Locality-Constrained Coding for Robust Visual Tracking.
IEEE Trans. Circuits Syst. Video Technol., 2017

Kernelized temporal locality learning for real-time visual tracking.
Pattern Recognit. Lett., 2017

Online learning and joint optimization of combined spatial-temporal models for robust visual tracking.
Neurocomputing, 2017

Indefinite Kernel Logistic Regression.
Proceedings of the 2017 ACM on Multimedia Conference, 2017

Correlation Filters with Adaptive Memories and Fusion for Visual Tracking.
Proceedings of the Neural Information Processing - 24th International Conference, 2017

Robust Kernel Approximation for Classification.
Proceedings of the Neural Information Processing - 24th International Conference, 2017

Visual tracking via structural patch-based dictionary pair learning.
Proceedings of the 2017 IEEE International Conference on Image Processing, 2017

2016
Co-saliency detection via inter and intra saliency propagation.
Signal Process. Image Commun., 2016

Robust visual tracking via constrained correlation filter coding.
Pattern Recognit. Lett., 2016

Geometric affine transformation estimation via correlation filter for visual tracking.
Neurocomputing, 2016

Incremental Robust Nonnegative Matrix Factorization for Object Tracking.
Proceedings of the Neural Information Processing - 23rd International Conference, 2016

Correlation filter tracking via bootstrap learning.
Proceedings of the 2016 IEEE International Conference on Image Processing, 2016

Robust visual tracking via inverse nonnegative matrix factorization.
Proceedings of the 2016 IEEE International Conference on Acoustics, 2016

2015
Visual Tracking via Nonnegative Regularization Multiple Locality Coding.
Proceedings of the 2015 IEEE International Conference on Computer Vision Workshop, 2015


  Loading...