67 citations · 176 across the 24 of their papers we have counts for
25 papers
Can overfitted deep neural networks in adversarial training generalize? -- An approximation viewpoint
Zhongjie Shi, Fanghui Liu, Yuan Cao +1
Adversarial training is a widely used method to improve the robustness of deep neural networks (DNNs) over adversarial perturbations. However, it is empirically observed that adver…
Federated Learning under Covariate Shifts with Generalization Guarantees
Ali Ramezani-Kebrya, Fanghui Liu, Thomas Pethick +2
This paper addresses intra-client and inter-client covariate shifts in federated learning (FL) with a focus on the overall generalization performance. To handle covariate shifts, w…
What can online reinforcement learning with function approximation benefit from general coverage conditions?
Fanghui Liu, Luca Viano, Volkan Cevher
In online reinforcement learning (RL), instead of employing standard structural assumptions on Markov decision processes (MDPs), using a certain coverage condition (original from o…
Benign Overfitting in Deep Neural Networks under Lazy Training
Zhenyu Zhu, Fanghui Liu, Grigorios G Chrysos +2
This paper focuses on over-parameterized deep neural networks (DNNs) with ReLU activation functions and proves that when the data distribution is well-separated, DNNs can achieve B…
Sound and Complete Verification of Polynomial Networks
Elias Abad Rocamora, Mehmet Fatih Sahin, Fanghui Liu +2
Polynomial Networks (PNs) have demonstrated promising performance on face and image recognition recently. However, robustness of PNs is unclear and thus obtaining certificates beco…
Extrapolation and Spectral Bias of Neural Nets with Hadamard Product: a Polynomial Net Study
Yongtao Wu, Zhenyu Zhu, Fanghui Liu +2
Neural tangent kernel (NTK) is a powerful tool to analyze training dynamics of neural networks and their generalization bounds. The study on NTK has been devoted to typical neural…
Understanding Deep Neural Function Approximation in Reinforcement Learning via -Greedy Exploration
Fanghui Liu, Luca Viano, Volkan Cevher
This paper provides a theoretical study of deep neural function approximation in reinforcement learning (RL) with the -greedy exploration under the online setting. This problem…
Random Fourier Features for Asymmetric Kernels
Mingzhen He, Fan He, Fanghui Liu +1
The random Fourier features (RFFs) method is a powerful and popular technique in kernel approximation for scalability of kernel methods. The theoretical foundation of RFFs is based…
Robustness in deep learning: The good (width), the bad (depth), and the ugly (initialization)
Zhenyu Zhu, Fanghui Liu, Grigorios G Chrysos +1
We study the average robustness notion in deep neural networks in (selected) wide and narrow, deep and shallow, as well as lazy and non-lazy training settings. We prove that in the…
Generalization Properties of NAS under Activation and Skip Connection Search
Zhenyu Zhu, Fanghui Liu, Grigorios G Chrysos +1
Neural Architecture Search (NAS) has fostered the automatic discovery of state-of-the-art neural architectures. Despite the progress achieved with NAS, so far there is little atten…
On the Double Descent of Random Features Models Trained with SGD
Fanghui Liu, Johan A. K. Suykens, Volkan Cevher
We study generalization properties of random features (RF) regression in high dimensions optimized by stochastic gradient descent (SGD) in under-/over-parameterized regime. In this…
Towards a Unified Quadrature Framework for Large-Scale Kernel Machines
Fanghui Liu, Xiaolin Huang, Yudong Chen +1
In this paper, we develop a quadrature framework for large-scale kernel machines via a numerical integration representation. Considering that the integration domain and measure of…
Kernel regression in high dimensions: Refined analysis beyond double descent
Fanghui Liu, Zhenyu Liao, Johan A. K. Suykens
In this paper, we provide a precise characterization of generalization properties of high dimensional kernel ridge regression across the under- and over-parameterized regimes, depe…
End-to-end Kernel Learning via Generative Random Fourier Features
Kun Fang, Fanghui Liu, Xiaolin Huang +1
Random Fourier features (RFFs) provide a promising way for kernel learning in a spectral case. Current RFFs-based kernel learning methods usually work in a two-stage way. In the fi…
Analysis of Regularized Least Squares in Reproducing Kernel Krein Spaces
Fanghui Liu, Lei Shi, Xiaolin Huang +2
In this paper, we study the asymptotic properties of regularized least squares with indefinite kernels in reproducing kernel Krein spaces (RKKS). By introducing a bounded hyper-sph…
Fast Learning in Reproducing Kernel Krein Spaces via Signed Measures
Fanghui Liu, Xiaolin Huang, Yingyi Chen +1
In this paper, we attempt to solve a long-lasting open question for non-positive definite (non-PD) kernels in machine learning community: can a given non-PD kernel be decomposed in…
Random Features for Kernel Approximation: A Survey on Algorithms, Theory, and Beyond
Fanghui Liu, Xiaolin Huang, Yudong Chen +1
Random features is one of the most popular techniques to speed up kernel methods in large-scale problems. Related works have been recognized by the NeurIPS Test-of-Time award in 20…
Random Fourier Features via Fast Surrogate Leverage Weighted Sampling
Fanghui Liu, Xiaolin Huang, Yudong Chen +2
In this paper, we propose a fast surrogate leverage weighted sampling strategy to generate refined random Fourier features for kernel approximation. Compared to the current state-o…
Deep Kernel Learning via Random Fourier Features
Jiaxuan Xie, Fanghui Liu, Kaijie Wang +1
Kernel learning methods are among the most effective learning methods and have been vigorously studied in the past decades. However, when tackling with complicated tasks, classical…
Robust Visual Tracking Revisited: From Correlation Filter to Template Matching
Fanghui Liu, Chen Gong, Xiaolin Huang +3
In this paper, we propose a novel matching based tracker by investigating the relationship between template matching and the recent popular correlation filter based trackers (CFTs)…
Generalization Properties of hyper-RKHS and its Applications
Fanghui Liu, Lei Shi, Xiaolin Huang +2
This paper generalizes regularized regression problems in a hyper-reproducing kernel Hilbert space (hyper-RKHS), illustrates its utility for kernel learning and out-of-sample exten…
Learning Data-adaptive Nonparametric Kernels
Fanghui Liu, Xiaolin Huang, Chen Gong +2
In this paper, we propose a data-adaptive non-parametric kernel learning framework in margin based kernel methods. In model formulation, given an initial kernel matrix, a data-adap…
Indefinite Kernel Logistic Regression with Concave-inexact-convex Procedure
Fanghui Liu, Xiaolin Huang, Chen Gong +2
In kernel methods, the kernels are often required to be positive definite, which restricts the use of many indefinite kernels. To consider those non-positive definite kernels, in t…
Visual Tracking via Nonnegative Regularization Multiple Locality Coding
Fanghui Liu, Tao Zhou, Irene Y. H. Gu +1
This paper presents a novel object tracking method based on approximated Locality-constrained Linear Coding (LLC). Rather than using a non-negativity constraint on encoding coeffic…