activity
20182025
collaborators

8 papers

cs.LG2020

Recurrence of Optimum for Training Weight and Activation Quantized Networks

Ziang Long, Penghang Yin, Jack Xin

Deep neural networks (DNNs) are quantized for efficient inference on resource-constrained platforms. However, training deep learning models with low-precision weights and activatio…

cs.LG2020

Learning Quantized Neural Nets by Coarse Gradient Method for Non-linear Classification

Ziang Long, Penghang Yin, Jack Xin

Quantized or low-bit neural networks are attractive due to their inference efficiency. However, training deep neural networks with quantized activations involves minimizing a disco…

cs.LG2020

Global Convergence and Geometric Characterization of Slow to Fast Weight Evolution in Neural Network Training for Classifying Linearly Non-Separable Data

Ziang Long, Penghang Yin, Jack Xin

In this paper, we study the dynamics of gradient descent in learning neural networks for classification problems. Unlike in existing works, we consider the linearly non-separable c…

cs.LG2019

Understanding Straight-Through Estimator in Training Activation Quantized Neural Nets

Penghang Yin, Jiancheng Lyu, Shuai Zhang +3

Training activation quantized neural networks involves minimizing a piecewise constant function whose gradient vanishes almost everywhere, which is undesirable for the standard bac…

math.OC2018

Non-ergodic Convergence Analysis of Heavy-Ball Algorithms

Tao Sun, Penghang Yin, Dongsheng Li +3

In this paper, we revisit the convergence of the Heavy-ball method, and present improved convergence complexity results in the convex setting. We provide the first non-ergodic O(1/…

cs.LG2018

Adversarial Defense via Data Dependent Activation Function and Total Variation Minimization

Bao Wang, Alex T. Lin, Wei Zhu +3

We improve the robustness of Deep Neural Net (DNN) to adversarial attacks by using an interpolating function as the output activation. This data-dependent activation remarkably imp…