• Publications
  • Influence
Tensor completion for estimating missing values in visual data
TLDR
An algorithm to estimate missing values in tensors of visual data by laying out the theoretical foundations and building a working algorithm is proposed, which is more accurate and robust than heuristic approaches.
Tensor Completion for Estimating Missing Values in Visual Data
TLDR
The contribution of this paper is to extend the matrix case to the tensor case by proposing the first definition of the trace norm for tensors and building a working algorithm to estimate missing values in tensors of visual data.
Generalized low rank approximations of matrices
  • Jieping Ye
  • Computer Science, Mathematics
    ICML
  • 4 July 2004
TLDR
This paper did extensive experiments on face image data to evaluate the effectiveness of the proposed algorithm and compare the computed low rank approximations with those obtained from traditional Singular Value Decomposition based method.
Fast and Accurate Matrix Completion via Truncated Nuclear Norm Regularization
TLDR
This paper proposes to achieve a better approximation to the rank of matrix by truncated nuclear norm, which is given by the nuclear norm subtracted by the sum of the largest few singular values, and develops a novel matrix completion algorithm by minimizing the Truncated Nuclear Norm.
Deep Multi-View Spatial-Temporal Network for Taxi Demand Prediction
TLDR
A Deep Multi-View Spatial-Temporal Network (DMVST-Net) framework to model both spatial and temporal relations is proposed, which demonstrates effectiveness of the approach over state-of-the-art methods.
Two-Dimensional Linear Discriminant Analysis
TLDR
2DLDA, a novel LDA algorithm, which stands for 2-Dimensional Linear Discriminant Analysis, overcomes the singularity problem implicitly, while achieving efficiency and the combination of 2DLDA and classical LDA, namely 2 DLDA+LDA, is studied.
An accelerated gradient method for trace norm minimization
TLDR
This paper exploits the special structure of the trace norm, based on which it is proposed an extended gradient algorithm that converges as O(1/k) and proposes an accelerated gradient algorithm, which achieves the optimal convergence rate of O( 1/k2) for smooth problems.
Characterization of a Family of Algorithms for Generalized Discriminant Analysis on Undersampled Problems
  • Jieping Ye
  • Mathematics, Computer Science
    J. Mach. Learn. Res.
  • 1 December 2005
TLDR
A generalized discriminant analysis based on a new optimization criterion that extends the optimization criteria of the classical Linear Discriminant Analysis (LDA) when the scatter matrices are singular is presented.
Multi-Task Feature Learning Via Efficient l2, 1-Norm Minimization
TLDR
This paper proposes to accelerate the computation of the l2, 1-norm regularized regression model by reformulating it as two equivalent smooth convex optimization problems which are then solved via the Nesterov's method---an optimal first-order black-box method for smooth conveX optimization.
A General Iterative Shrinkage and Thresholding Algorithm for Non-convex Regularized Optimization Problems
TLDR
A General Iterative Shrinkage and Thresholding (GIST) algorithm to solve the nonconvex optimization problem for a large class of non-conveX penalties and a detailed convergence analysis of the GIST algorithm is presented.
...
1
2
3
4
5
...