Search Results - "Penghang Yin, Penghang Yin"

SCRABBLE: single-cell RNA-seq imputation constrained by bulk RNA-seq data by Peng, Tao, Zhu, Qin, Yin, Penghang, Tan, Kai

“…Single-cell RNA-seq data contain a large proportion of zeros for expressed genes. Such dropout events present a fundamental challenge for various types of data…”
Get full text

Quantization and Training of Low Bit-Width Convolutional Neural Networks for Object Detection by Penghang Yin, Penghang Yin, Shuai Zhang, Shuai Zhang, Yingyong Qi, Yingyong Qi, Jack Xin, Jack Xin

Get full text

Iterative $ℓ_1$ Minimization for Non-Convex Compressed Sensing by Penghang Yin, Penghang Yin, Jack Xin, Jack Xin

Get full text

Deep Learning for Real-Time Crime Forecasting and Its Ternarization by Wang, Bao, Yin, Penghang, Bertozzi, Andrea Louise, Brantingham, P. Jeffrey, Osher, Stanley Joel, Xin, Jack

“…Real-time crime forecasting is important. However, accurate prediction of when and where the next crime will happen is difficult. No known physical model…”
Get full text

Learning quantized neural nets by coarse gradient method for nonlinear classification by Long, Ziang, Yin, Penghang, Xin, Jack

“…Quantized or low-bit neural networks are attractive due to their inference efficiency. However, training deep neural networks with quantized activations…”
Get full text

Feature Affinity Assisted Knowledge Distillation and Quantization of Deep Neural Networks on Label-Free Data by Li, Zhijian, Yang, Biao, Yin, Penghang, Qi, Yingyong, Xin, Jack

“…In this paper, we propose a feature affinity (FA) assisted knowledge distillation (KD) method to improve quantization-aware training of deep neural networks…”
Get full text

Laplacian smoothing gradient descent by Osher, Stanley, Wang, Bao, Yin, Penghang, Luo, Xiyang, Barekat, Farzin, Pham, Minh, Lin, Alex

“…We propose a class of very simple modifications of gradient descent and stochastic gradient descent leveraging Laplacian smoothing. We show that when applied…”
Get full text

ITERATIVE l1 MINIMIZATION FOR NON-CONVEX COMPRESSED SENSING by Yin, Penghang, Xin, Jack

“…An algorithmic framework, based on the difference of convex functions algorithm （D- CA）, is proposed for minimizing a class of concave sparse metrics for…”
Get full text

Computations of Optimal Transport Distance with Fisher Information Regularization by Li, Wuchen, Yin, Penghang, Osher, Stanley

“…We propose a fast algorithm to approximate the optimal transport distance. The main idea is to add a Fisher information regularization into the dynamical…”
Get full text

Recurrence of optimum for training weight and activation quantized networks by Long, Ziang, Yin, Penghang, Xin, Jack

“…Deep neural networks (DNNs) are quantized for efficient inference on resource-constrained platforms. However, training deep learning models with low-precision…”
Get full text

Point Source Super-resolution Via Non-convex L1 Based Methods by Lou, Yifei, Yin, Penghang, Xin, Jack

“…We study the super-resolution (SR) problem of recovering point sources consisting of a collection of isolated and suitably separated spikes from only the low…”
Get full text

Generalized proximal smoothing (GPS) for phase retrieval by Pham, Minh, Yin, Penghang, Rana, Arjun, Osher, Stanley, Miao, Jianwei

“…Not provided…”
Get full text

Stochastic Backward Euler: An Implicit Gradient Descent Algorithm for k-Means Clustering by Yin, Penghang, Pham, Minh, Oberman, Adam, Osher, Stanley

“…In this paper, we propose an implicit gradient descent algorithm for the classic k -means problem. The implicit gradient step or backward Euler is solved via…”
Get full text

Linear Feature Transform and Enhancement of Classification on Deep Neural Network by Yin, Penghang, Xin, Jack, Qi, Yingyong

“…A weighted and convex regularized nuclear norm model is introduced to construct a rank constrained linear transform on feature vectors of deep neural networks…”
Get full text

Generalized proximal smoothing (GPS) for phase retrieval by Pham, Minh, Yin, Penghang, Rana, Arjun, Osher, Stanley, Miao, Jianwei

“…In this paper, we report the development of the generalized proximal smoothing (GPS) algorithm for phase retrieval of noisy data. GPS is a optimization-based…”
Get full text

Alternating direction method of multipliers with difference of convex functions by Sun, Tao, Yin, Penghang, Cheng, Lizhi, Jiang, Hao

“…In this paper, we consider the minimization of a class of nonconvex composite functions with difference of convex structure under linear constraints. While…”
Get full text

Blended coarse gradient descent for full quantization of deep neural networks by Yin, Penghang, Zhang, Shuai, Lyu, Jiancheng, Osher, Stanley, Qi, Yingyong, Xin, Jack

“…Quantized deep neural networks (QDNNs) are attractive due to their much lower memory storage and faster inference speed than their regular full-precision…”
Get full text

l^sub 1^-minimization method for link flow correction by Yin, Penghang, Sun, Zhe, Jin, Wen-Long, Xin, Jack

“…A computational method, based on ℓ1-minimization, is proposed for the problem of link flow correction, when the available traffic flow data on many links in a…”
Get full text

Unbalanced and Partial L1 Monge–Kantorovich Problem: A Scalable Parallel First-Order Method by Ryu, Ernest K., Li, Wuchen, Yin, Penghang, Osher, Stanley

“…We propose a new algorithm to solve the unbalanced and partial L 1 -Monge–Kantorovich problems. The proposed method is a first-order primal-dual method that is…”
Get full text

Point Source Super-resolution Via Non-convex $$L_1$$ Based Methods by Lou, Yifei, Yin, Penghang, Xin, Jack

Get full text