325 citations · 3.5k across the 148 of their papers we have counts for
14 papers · 1 filter
Identifiability and Asymptotics in Learning Homogeneous Linear ODE Systems from Discrete Observations
Yuanyuan Wang, Wei Huang, Mingming Gong +4
Ordinary Differential Equations (ODEs) have recently gained a lot of attention in machine learning. However, the theoretical aspects, e.g., identifiability and asymptotic propertie…
Instance-dependent Label-noise Learning under a Structural Causal Model
Yu Yao, Tongliang Liu, Mingming Gong +3
Label noise will degenerate the performance of deep learning algorithms because deep neural networks easily overfit label errors. Let X and Y denote the instance and clean label, r…
Transferring Knowledge Fragments for Learning Distance Metric from A Heterogeneous Domain
Yong Luo, Yonggang Wen, Tongliang Liu +1
The goal of transfer learning is to improve the performance of target learning task by leveraging information (or transferring knowledge) from other related tasks. In this paper, w…
Multi-View Matrix Completion for Multi-Label Image Classification
Yong Luo, Tongliang Liu, Dacheng Tao +1
There is growing interest in multi-label image classification due to its critical role in web-based image analytics-based applications, such as large-scale image retrieval and brow…
Why ResNet Works? Residuals Generalize
Fengxiang He, Tongliang Liu, Dacheng Tao
Residual connections significantly boost the performance of deep neural networks. However, there are few theoretical results that address the influence of residuals on the hypothes…
An Optimal Transport View on Generalization
Jingwei Zhang, Tongliang Liu, Dacheng Tao
We derive upper bounds on the generalization error of learning algorithms based on their \emph{algorithmic transport cost}: the expected Wasserstein distance between the output hyp…
An Information-Theoretic View for Deep Learning
Jingwei Zhang, Tongliang Liu, Dacheng Tao
Deep learning has transformed computer vision, natural language processing, and speech recognition\cite{badrinarayanan2017segnet, dong2016image, ren2017faster, ji20133d}. However,…
On the Rates of Convergence from Surrogate Risk Minimizers to the Bayes Optimal Classifier
Jingwei Zhang, Tongliang Liu, Dacheng Tao
We study the rates of convergence from empirical surrogate risk minimizers to the Bayes optimal classifier. Specifically, we introduce the notion of \emph{consistency intensity} to…
Learning with Biased Complementary Labels
Xiyu Yu, Tongliang Liu, Mingming Gong +1
In this paper, we study the classification problem in which we have access to easily obtainable surrogate for true labels, namely complementary labels, which specify classes that o…
Learning with Bounded Instance- and Label-dependent Label Noise
Jiacheng Cheng, Tongliang Liu, Kotagiri Ramamohanarao +1
Instance- and Label-dependent label Noise (ILN) widely exists in real-world datasets but has been rarely studied. In this paper, we focus on Bounded Instance- and Label-dependent l…
Transfer Learning with Label Noise
Xiyu Yu, Tongliang Liu, Mingming Gong +3
Transfer learning aims to improve learning in target domain by borrowing knowledge from a related but different source domain. To reduce the distribution shift between source and t…
Algorithmic stability and hypothesis complexity
Tongliang Liu, Gábor Lugosi, Gergely Neu +1
We introduce a notion of algorithmic stability of learning algorithms---that we term \emph{argument stability}---that captures stability of the hypothesis output by the learning al…
Dimensionality-Dependent Generalization Bounds for -Dimensional Coding Schemes
Tongliang Liu, Dacheng Tao, Dong Xu
The -dimensional coding schemes refer to a collection of methods that attempt to represent data using a set of representative -dimensional vectors, and include non-negative m…
Local Rademacher Complexity for Multi-label Learning
Chang Xu, Tongliang Liu, Dacheng Tao +1
We analyze the local Rademacher complexity of empirical risk minimization (ERM)-based multi-label learning algorithms, and in doing so propose a new algorithm for multi-label learn…