-
Monocular 3D Pose Recovery via Nonconvex Sparsity with Theoretical Analysis
For recovering 3D object poses from 2D images, a prevalent method is to ...
12/29/2018 ∙ by Jianqiao Wangni, et al. ∙
24
∙
share
read it
-
Trajectory Normalized Gradients for Distributed Optimization
Recently, researchers proposed various low-precision gradient compressio...
01/24/2019 ∙ by Jianqiao Wangni, et al. ∙
14
∙
share
read it
-
Learning Sparse Visual Representations with Leaky Capped Norm Regularizers
Sparsity inducing regularization is an important part for learning over-...
11/08/2017 ∙ by Jianqiao Wangni, et al. ∙
0
∙
share
read it
-
Stochastic Orthant-Wise Limited-Memory Quasi-Newton Methods
The ℓ_1-regularized sparse model has been popular in machine learning so...
04/26/2017 ∙ by Jianqiao Wangni, et al. ∙
0
∙
share
read it
-
Learning Random Fourier Features by Hybrid Constrained Optimization
The kernel embedding algorithm is an important component for adapting ke...
12/07/2017 ∙ by Jianqiao Wangni, et al. ∙
0
∙
share
read it
-
Gradient Sparsification for Communication-Efficient Distributed Optimization
Modern large scale machine learning applications require stochastic opti...
10/26/2017 ∙ by Jianqiao Wangni, et al. ∙
0
∙
share
read it
-
Normalized Diversification
Generating diverse yet specific data is the goal of the generative adver...
04/07/2019 ∙ by Shaohui Liu, et al. ∙
0
∙
share
read it
Jianqiao Wangni
is this you? claim profile
AI Lab Researcher & Developer at Tencent AI Lab, Research Assistant at The Chinese University of Hong Kong 2015 and Research Assistant at Tsinghua University 2015.
