No abstract

In this work, we study the problem of learning a single model for multiple domains. Unlike the conventional machine learning scenario where each domain can have the corresponding model, multiple domains (i.e., applications/users) may share the same machine learning model due to maintenance loads in cloud computing services. For example, a digit-recognition model should be applicable to hand-written digits, house numbers, car plates, etc. Therefore, an ideal model for cloud computing has to perform well at each applicable domain. To address this new challenge from cloud computing, we develop a framework of robust optimization over multiple domains. In lieu of minimizing the empirical risk, we aim to learn a model optimized to the adversarial distribution over multiple domains. Hence, we propose to learn the model and the adversarial distribution simultaneously with the stochastic algorithm for efficiency. Theoretically, we analyze the convergence rate for convex and non-convex models. To our best knowledge, we first study the convergence rate of learning a robust non-convex model with a practical algorithm. Furthermore, we demonstrate that the robustness of the framework and the convergence rate can be further enhanced by appropriate regularizers over the adversarial distribution. The empirical study on real-world fine-grained visual categorization and digits recognition tasks verifies the effectiveness and efficiency of the proposed framework.

Aim: This study investigated the clinical characteristics of internet addiction using a cross-sectional survey and psychiatric interview. Methods:A structured questionnaire consisted of demographics, Symptom Checklist 90, Self-Rating Anxiety Scale, Self-Rating Depression Scale, and Young's Internet Addiction Test (YIAT) was administered to students of two secondary schools in Wuhan, China. Students with a score of 5 or higher on the YIAT were classified as having Internet Addiction Disorder (IAD). Two psychiatrists interviewed students with IAD to confirm the diagnosis and evaluate their clinical characteristics.Results: Of a total of 1076 respondents (mean age 15.4 ± 1.7 years; 54.1% boys), 12.6% (n = 136) met the YIAT criteria for IAD. Clinical interviews ascertained the Internet addiction of 136 pupils and also identified 20 students (14.7% of IAD group) with comorbid psychiatric disorders. Results from multinomial logistic regression indicated that being male, in grade 7-9, poor relationship between parents and higher self-reported depression scores were significantly associated with the diagnosis of IAD. Conclusion:These results advance our understanding of the clinical characteristics of Internet addiction in Chinese secondary school students and may help clinicians, teachers, and other stakeholders better manage this increasingly serious mental condition.

No abstract