Author name cluster

Shuyang Wang

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

5 papers

2 author rows

UAI Conference 2025 Conference Paper

A Mirror Descent Perspective of Smoothed Sign Descent

Shuyang Wang
Diego Klabjan

The optimization dynamics of gradient descent for overparameterized problems can be viewed as low-dimensional dual dynamics induced by a mirror map, providing a mirror descent perspective on the implicit regularization phenomenon. However, the dynamics of adaptive gradient descent methods that are widely used in practice remain less understood. Meanwhile, empirical evidence of performance gaps suggests fundamental differences in their underlying dynamics. In this work, we introduce the dual dynamics of smoothed sign descent with stability constant $\varepsilon$ for regression problems, formulated using the mirror descent framework. Unlike prior methods, our approach applies to algorithms where update directions deviate from true gradients such as ADAM. We propose a mirror map that reveals the equivalent dual dynamics under some assumptions. By studying dual dynamics, we characterize the convergent solution as approximately minimizing a Bregman divergence style function closely related to the $l_{3/2}$ norm. Furthermore, we demonstrate the role of the stability constant $\varepsilon$ in shaping the convergent solution. Our analyses offer new insights into the distinct properties of the smoothed sign descent algorithm, and show the potential of applying the mirror descent framework to study complex dynamics beyond gradient descent.

Details

AAAI Conference 2017 Conference Paper

Examples-Rules Guided Deep Neural Network for Makeup Recommendation

Taleb Alashkar
Songyao Jiang
Shuyang Wang
Yun Fu

In this paper, we consider a fully automatic makeup recommendation system and propose a novel examples-rules guided deep neural network approach. The framework consists of three stages. First, makeup-related facial traits are classiﬁed into structured coding. Second, these facial traits are fed into examples-rules guided deep neural recommendation model which makes use of the pairwise of Before-After images and the makeup artist knowledge jointly. Finally, to visualize the recommended makeup style, an automatic makeup synthesis system is developed as well. To this end, a new Before-After facial makeup database is collected and labeled manually, and the knowledge of makeup artist is modeled by knowledge base system. The performance of this framework is evaluated through extensive experimental analyses. The experiments validate the automatic facial traits classiﬁcation, the recommendation effectiveness in statistical and perceptual ways and the makeup synthesis accuracy which outperforms the state of the art methods by large margin. It is also worthy to note that the proposed framework is a pioneering fully automatic makeup recommendation systems to our best knowledge.

PDF Details

AAAI Conference 2017 Conference Paper

Feature Selection Guided Auto-Encoder

Shuyang Wang
Zhengming Ding
Yun Fu

Recently the auto-encoder and its variants have demonstrated their promising results in extracting effective features. Specifically, its basic idea of encouraging the output to be as similar as input, ensures the learned representation could faithfully reconstruct the input data. However, one problem arises that not all hidden units are useful to compress the discriminative information while lots of units mainly contribute to represent the task-irrelevant patterns. In this paper, we propose a novel algorithm, Feature Selection Guided Auto-Encoder, which is a uniﬁed generative model that integrates feature selection and auto-encoder together. To this end, our proposed algorithm can distinguish the task-relevant units from the task-irrelevant ones to obtain most effective features for future classiﬁcation tasks. Our model not only performs feature selection on learned high-level features, but also dynamically endows the auto-encoder to produce more discriminative units. Experiments on several benchmarks demonstrate our method’s superiority over state-of-the-art approaches.

PDF Details

IJCAI Conference 2016 Conference Paper

Coupled Marginalized Auto-Encoders for Cross-Domain Multi-View Learning

Shuyang Wang
Zhengming Ding
Yun Fu

In cross-domain learning, there is a more challenging problem that the domain divergence involves more than one dominant factors, e. g. , different view-points, various resolutions and changing illuminations. Fortunately, an intermediate domain could often be found to build a bridge across them to facilitate the learning problem. In this paper, we propose a Coupled Marginalized Denoising Auto-encoders framework to address the cross-domain problem. Specifically, we design two marginalized denoising auto-encoders, one for the target and the other for source as well as the intermediate one. To better couple the two denoising auto-encoders learning, we incorporate a feature mapping, which tends to transfer knowledge between the intermediate domain and the target one. Furthermore, the maximum margin criterion, e. g. , intra-class compactness and inter-class penalty, on the output layer is imposed to seek more discriminative features across different domains. Extensive experiments on two tasks have demonstrated the superiority of our method over the state-of-the-art methods.

PDF Details

AAAI Conference 2016 Conference Paper

Face Behind Makeup

Shuyang Wang
Yun Fu

In this work, we propose a novel automatic makeup detector and remover framework. For makeup detector, a localityconstrained low-rank dictionary learning algorithm is used to determine and locate the usage of cosmetics. For the challenging task of makeup removal, a locality-constrained coupled dictionary learning (LC-CDL) framework is proposed to synthesize non-makeup face, so that the makeup could be erased according to the style. Moreover, we build a stepwise makeup dataset (SMU) which to the best of our knowledge is the ﬁrst dataset with procedures of makeup. This novel technology itself carries many practical applications, e. g. products recommendation for consumers; user-speciﬁed makeup tutorial; security applications on makeup face veriﬁcation. Finally, our system is evaluated on three existing (VMU, MIW, YMU) and one own-collected makeup datasets. Experimental results have demonstrated the effectiveness of DL-based method on makeup detection. The proposed LC-CDL shows very promising performance on makeup removal regarding on the structure similarity. In addition, the comparison of face veriﬁcation accuracy with presence or absence of makeup is presented, which illustrates an application of our automatic makeup remover system in the context of face veriﬁcation with facial makeup.

PDF Details