J. Xin

activity

20012023

most citedA convex model for non-negative matrix factorization and dimensionality reduction on physical space

169 citations · 361 across the 53 of their papers we have counts for

collaborators

Showing 2018Show all

3 papers · 1 filter

math.OC2018★ 5 cited

Convergence of a Relaxed Variable Splitting Method for Learning Sparse Neural Networks via $ℓ_{1}, ℓ_{0}$ , and transformed- $ℓ_{1}$ Penalties

Thu Dinh, Jack Xin

Sparsification of neural networks is one of the effective complexity reduction methods to improve efficiency and generalizability. We consider the problem of learning a one hidden…

cs.LG2018★ 12 cited

Blended Coarse Gradient Descent for Full Quantization of Deep Neural Networks

Penghang Yin, Shuai Zhang, Jiancheng Lyu +3

Quantized deep neural networks (QDNNs) are attractive due to their much lower memory storage and faster inference speed than their regular full precision counterparts. To maintain…

cs.CV2018★ 9 cited

BinaryRelax: A Relaxation Approach For Training Deep Neural Networks With Quantized Weights

Penghang Yin, Shuai Zhang, Jiancheng Lyu +3

We propose BinaryRelax, a simple two-phase algorithm, for training deep neural networks with quantized weights. The set constraint that characterizes the quantization of weights is…

Convergence of a Relaxed Variable Splitting Method for Learning Sparse Neural Networks via ℓ1​,ℓ0​, and transformed-ℓ1​ Penalties

Blended Coarse Gradient Descent for Full Quantization of Deep Neural Networks

BinaryRelax: A Relaxation Approach For Training Deep Neural Networks With Quantized Weights

Convergence of a Relaxed Variable Splitting Method for Learning Sparse Neural Networks via $ℓ_{1}, ℓ_{0}$ , and transformed- $ℓ_{1}$ Penalties