Shuai Zhang

Dr. Shuai Zhang

orcid

Research Focus & Metrics

Academic Career Length

15Years (2012-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications

1 January 2017 in Communications in Mathematical Sciences
Verified
Journal Article
Open access
PDF file
SZShuai Zhang
Shuai Zhang
JXJack Xin
Jack Xin
International Press of Boston - publishers of scholarly mathematical and scientific journals and books

1 January 2017 in Communications in Mathematical Sciences
Verified
Journal Article
Open access
PDF file
SZShuai Zhang
Shuai Zhang
PYPenghang Yin
Penghang Yin
JXJack Xin
Jack Xin
International Press of Boston - publishers of scholarly mathematical and scientific journals and books

25 September 2019 in arXiv
Verified
Preprint
Open access
PDF file
PYPenghang Yin
Penghang Yin
JLJiancheng Lyu
Jiancheng Lyu
SZShuai Zhang
Shuai Zhang
SOStanley Osher
Stanley Osher
YQYingyong Qi
Yingyong Qi
JXJack Xin
Jack Xin
Training activation quantized neural networks involves minimizing a piecewise constant function whose gradient vanishes almost everywhere, which is undesirable for the standard back-propagation or chain rule. An empirical way around this issue is to use a straight-through estimator (STE) (Bengio et al., 2013) in the backward pass only, so that the "gradient" through the modified chain rule becomes non-trivial. Since this unusual "gradient" is certainly not the gradient of loss function, the following question arises: why searching in its negative direction minimizes the training loss? In this paper, we provide the theoretical justification of the concept of STE by answering this question. We consider the problem of learning a two-linear-layer network with binarized ReLU activation and Gaussian input data. We shall refer to the unusual "gradient" given by the STE-modifed chain rule as coarse gradient. The choice of STE is not unique. We prove that if the STE is properly chosen, the expected coarse gradient correlates positively with the population gradient (not available for the training), and its negation is a descent direction for minimizing the population loss. We further show the associated coarse gradient descent algorithm converges to a critical point of the population loss minimization problem. Moreover, we show that a poor choice of STE leads to instability of the training algorithm near certain local minima, which is verified with CIFAR-10 experiments.

6 January 2019 in arXiv
Verified
Preprint
Open access
PDF file
PYPenghang Yin
Penghang Yin
SZShuai Zhang
Shuai Zhang
JLJiancheng Lyu
Jiancheng Lyu
SOStanley Osher
Stanley Osher
YQYingyong Qi
Yingyong Qi
JXJack Xin
Jack Xin
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 the same performance level especially at low bit-widths, QDNNs must be retrained. Their training involves piecewise constant activation functions and discrete weights, hence mathematical challenges arise. We introduce the notion of coarse gradient and propose the blended coarse gradient descent (BCGD) algorithm, for training fully quantized neural networks. Coarse gradient is generally not a gradient of any function but an artificial ascent direction. The weight update of BCGD goes by coarse gradient correction of a weighted average of the full precision weights and their quantization (the so-called blending), which yields sufficient descent in the objective value and thus accelerates the training. Our experiments demonstrate that this simple blending technique is very effective for quantization at extremely low bit-width such as binarization. In full quantization of ResNet-18 for ImageNet classification task, BCGD gives 64.36\% top-1 accuracy with binary weights across all layers and 4-bit adaptive activation. If the weights in the first and last layers are kept in full precision, this number increases to 65.46\%. As theoretical justification, we show convergence analysis of coarse gradient descent for a two-linear-layer neural network model with Gaussian input data, and prove that the expected coarse gradient correlates positively with the underlying true gradient.