2025
Generalization Performance of Empirical Risk Minimization on Over-Parameterized Deep ReLU Nets.
IEEE Trans. Inf. Theory, March, 2025
Feature Qualification by Deep Nets: A Constructive Approach.
CoRR, March, 2025
2024
Sketching with Spherical Designs for Noisy Data Fitting on Spheres.
SIAM J. Sci. Comput., February, 2024
Kernel Interpolation of High Dimensional Scattered Data.
SIAM J. Numer. Anal., 2024
Weighted Spectral Filters for Kernel Interpolation on Spheres: Estimates of Prediction Accuracy for Noisy Data.
SIAM J. Imaging Sci., 2024
Component-based Sketching for Deep ReLU Nets.
CoRR, 2024
Lepskii Principle for Distributed Kernel Ridge Regression.
CoRR, 2024
Integral Operator Approaches for Scattered Data Fitting on Spheres.
CoRR, 2024
2023
Construction of Deep ReLU Nets for Spatially Sparse Learning.
IEEE Trans. Neural Networks Learn. Syst., October, 2023
Adaptive Parameter Selection for Kernel Ridge Regression.
CoRR, 2023
Lifting the Veil: Unlocking the Power of Depth in Q-learning.
CoRR, 2023
Distributed Uncertainty Quantification of Kernel Interpolation on Spheres.
CoRR, 2023
Adaptive Distributed Kernel Ridge Regression: A Feasible Distributed Learning Scheme for Data Silos.
CoRR, 2023
Optimal Approximation and Learning Rates for Deep Convolutional Neural Networks.
CoRR, 2023
Deep Convolutional Neural Networks with Zero-Padding: Feature Extraction and Learning.
CoRR, 2023
Kernel-Based Distributed Q-Learning: A Scalable Reinforcement Learning Approach for Dynamic Treatment Regimes.
CoRR, 2023
Explore the Power of Dropout on Few-shot Learning.
CoRR, 2023
An Effective Crop-Paste Pipeline for Few-shot Object Detection.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023
Explore the Power of Synthetic Data on Few-shot Object Detection.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023
2022
Realization of Spatial Sparseness by Deep ReLU Nets With Massive Data.
IEEE Trans. Neural Networks Learn. Syst., 2022
Distributed Learning With Dependent Samples.
IEEE Trans. Inf. Theory, 2022
Universal Consistency of Deep Convolutional Neural Networks.
IEEE Trans. Inf. Theory, 2022
Learning With Selected Features.
IEEE Trans. Cybern., 2022
Depth Selection for Deep ReLU Nets in Feature Extraction and Generalization.
IEEE Trans. Pattern Anal. Mach. Intell., 2022
Fully corrective gradient boosting with squared hinge: Fast learning rates and early stopping.
Neural Networks, 2022
Nystrom Regularization for Time Series Forecasting.
J. Mach. Learn. Res., 2022
Toward Efficient Ensemble Learning with Structure Constraints: Convergent Algorithms and Applications.
INFORMS J. Comput., 2022
A Unified Framework with Meta-dropout for Few-shot Learning.
CoRR, 2022
Three-stage Training Pipeline with Patch Random Drop for Few-shot Object Detection.
Proceedings of the Computer Vision - ACCV 2022, 2022
2021
Random Sketching for Neural Networks With ReLU.
IEEE Trans. Neural Networks Learn. Syst., 2021
Deep Neural Network Based Vehicle and Pedestrian Detection for Autonomous Driving: A Survey.
IEEE Trans. Intell. Transp. Syst., 2021
Distributed Filtered Hyperinterpolation for Noisy Data on the Sphere.
SIAM J. Numer. Anal., 2021
On ADMM in Deep Learning: Convergence and Saturation-Avoidance.
J. Mach. Learn. Res., 2021
Radial Basis Function Approximation with Distributively Stored Data on Spheres.
CoRR, 2021
2020
Realizing Data Features by Deep Nets.
IEEE Trans. Neural Networks Learn. Syst., 2020
Learning Through Deterministic Assignment of Hidden Parameters.
IEEE Trans. Cybern., 2020
Distributed Kernel Ridge Regression with Communications.
J. Mach. Learn. Res., 2020
Kernel-based L_2-Boosting with Structure Constraints.
CoRR, 2020
Distributed Learning with Dependent Samples.
CoRR, 2020
2019
Rescaled Boosting in Classification.
IEEE Trans. Neural Networks Learn. Syst., 2019
Generalization and Expressivity for Deep Nets.
IEEE Trans. Neural Networks Learn. Syst., 2019
Unified Low-Rank Matrix Estimate via Penalized Matrix Least Squares Approximation.
IEEE Trans. Neural Networks Learn. Syst., 2019
Constructive Neural Network Learning.
IEEE Trans. Cybern., 2019
Fast Learning With Polynomial Kernels.
IEEE Trans. Cybern., 2019
Boosted Kernel Ridge Regression: Optimal Learning Rates and Early Stopping.
J. Mach. Learn. Res., 2019
Nonparametric regression using needlet kernels for spherical data.
J. Complex., 2019
Deep Net Tree Structure for Balance of Capacity and Approximation Ability.
Frontiers Appl. Math. Stat., 2019
Fast Polynomial Kernel Classification for Massive Data.
CoRR, 2019
Deep Neural Networks for Rotation-Invariance Approximation and Learning.
CoRR, 2019
A Convergence Analysis of Nonlinearly Constrained ADMM in Deep Learning.
CoRR, 2019
Global Convergence of Block Coordinate Descent in Deep Learning.
Proceedings of the 36th International Conference on Machine Learning, 2019
High-Resolution Driving Scene Synthesis Using Stacked Conditional Gans and Spectral Normalization.
Proceedings of the IEEE International Conference on Multimedia and Expo, 2019
2018
Greedy Criterion in Orthogonal Greedy Learning.
IEEE Trans. Cybern., 2018
Corrigendum to "GAITA: A Gauss-Seidel iterative thresholding algorithm for l<sub>q</sub> regularized least squares regression" [J. Comput. Appl. Math. 319 (2017) 220-235].
J. Comput. Appl. Math., 2018
Construction of Neural Networks for Realization of Localized Deep Learning.
Frontiers Appl. Math. Stat., 2018
Block Coordinate Descent for Deep Learning: Unified Convergence Guarantees.
CoRR, 2018
Generalization Bounds for Regularized Pairwise Learning.
Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, 2018
2017
Shrinkage Degree in L<sub>2</sub>-Rescale Boosting for Regression.
IEEE Trans. Neural Networks Learn. Syst., 2017
Limitations of shallow nets approximation.
Neural Networks, 2017
Learning Rates for Classification with Gaussian Kernels.
Neural Comput., 2017
Distributed Learning with Regularized Least Squares.
J. Mach. Learn. Res., 2017
Distributed Semi-supervised Learning with Kernel Ridge Regression.
J. Mach. Learn. Res., 2017
GAITA: A Gauss-Seidel iterative thresholding algorithm for ℓ<sub>q</sub> regularized least squares regression.
J. Comput. Appl. Math., 2017
2016
Sparse Regularization: Convergence Of Iterative Jumping Thresholding Algorithm.
IEEE Trans. Signal Process., 2016
Learning and approximation capabilities of orthogonal super greedy algorithm.
Knowl. Based Syst., 2016
Linear and nonlinear approximation of spherical radial basis function networks.
J. Complex., 2016
Simultaneous approximation by spherical neural networks.
Neurocomputing, 2016
Greedy Criterion in Orthogonal Greedy Learning.
CoRR, 2016
Divide and Conquer Local Average Regression.
CoRR, 2016
Learning capability of the truncated greedy algorithm.
Sci. China Inf. Sci., 2016
2015
Is Extreme Learning Machine Feasible? A Theoretical Assessment (Part I).
IEEE Trans. Neural Networks Learn. Syst., 2015
Is Extreme Learning Machine Feasible? A Theoretical Assessment (Part II).
IEEE Trans. Neural Networks Learn. Syst., 2015
Error Estimate for Spherical Neural Networks Interpolation.
Neural Process. Lett., 2015
Jackson-type inequalities for spherical neural networks with doubling weights.
Neural Networks, 2015
A Gauss-Seidel Iterative Thresholding Algorithm for lq Regularized Least Squares Regression.
CoRR, 2015
Shrinkage degree in L<sub>2</sub>-re-scale boosting for regression.
CoRR, 2015
Re-scale boosting for regression and classification.
CoRR, 2015
2014
L<sub>1/2</sub> Regularization: Convergence of Iterative Half Thresholding Algorithm.
IEEE Trans. Signal Process., 2014
Sparse solution of underdetermined linear equations via adaptively iterative thresholding.
Signal Process., 2014
Learning Rates of <i>l<sup>q</sup></i> Coefficient Regularization Learning with Gaussian Kernel.
Neural Comput., 2014
Almost optimal estimates for approximation and learning by radial basis function networks.
Mach. Learn., 2014
Greedy metrics in orthogonal greedy learning.
CoRR, 2014
Learning and approximation capability of orthogonal super greedy algorithm.
CoRR, 2014
2013
Learning Capability of Relaxed Greedy Algorithms.
IEEE Trans. Neural Networks Learn. Syst., 2013
Learning rates of l<sup>q</sup> coefficient regularization learning with Gaussian kernel.
CoRR, 2013
Approximation by neural networks with scattered data.
Appl. Math. Comput., 2013
2012
A general radial quasi-interpolation operator on the sphere.
J. Approx. Theory, 2012
2011
Essential rate for approximation by spherical neural networks.
Neural Networks, 2011
2010
Constructive approximate interpolation by neural networks in the metric space.
Math. Comput. Model., 2010
Approximation capability of interpolation neural networks.
Neurocomputing, 2010