This paper focuses on stochastic methods for solving smooth non-convex strongly-concave min-max problems, which have received increasing attention due to their potential applications in deep learning (e.g., deep AUC m...
详细信息
This paper focuses on stochastic methods for solving smooth non-convex strongly-concave min-max problems, which have received increasing attention due to their potential applications in deep learning (e.g., deep AUC maximization, distributionally robust optimization). However, most of the existing algorithms are slow in practice, and their analysis revolves around the convergence to a nearly stationary point. We consider leveraging the Polyak-Łojasiewicz (PL) condition to design faster stochastic algorithms with stronger convergence guarantee. Although PL condition has been utilized for designing many stochastic minimization algorithms, their applications for non-convex min-max optimization remain rare. In this paper, we propose and analyze a generic framework of proximal stage-based method with many well-known stochastic updates embeddable. Fast convergence is established in terms of both the primal objective gap and the duality gap. Compared with existing studies, (i) our analysis is based on a novel Lyapunov function consisting of the primal objective gap and the duality gap of a regularized function, and (ii) the results are more comprehensive with improved rates that have better dependence on the condition number under different assumptions. We also conduct deep and non-deep learning experiments to verify the effectiveness of our methods.
As one of the most popular vision applications, face verification systems can be needed in all kinds of scenarios, including resource-constrained environments. In this paper, we propose a trimmed variant of MobileFace...
详细信息
In this paper we present the exploration of indoor positioning technologies for UAV s, and navigation techniques for path planning and obstacle avoidance. For the indoor positioning techniques, we employed Visual-Iner...
详细信息
This paper explores the convergence of physical and computational components in Cyber-Physical Systems (CPS). Security, trust, and privacy are paramount for reliable and resilient operation of these interconnected sys...
详细信息
Generative AI assistants are AI-powered applications that can provide personalized responses to user queries or prompts. A variety of AI assistants have recently been released, and among the most popular is OpenAI'...
详细信息
Gas leaks and fires present dangers that require detection and decisive action to protect lives and property. This paper specifically proposes cutting-edge sensor technologies with intelligent threshold algorithms and...
详细信息
Battery health monitoring methods including machine learning (ML) models rely on trustworthiness of battery sensor data and features. As more battery systems require network connectivity for intelligent health monitor...
详细信息
Survival prediction often involves estimating the time-to-event distribution from censored datasets. Previous approaches have focused on enhancing discrimination and marginal calibration. In this paper, we highlight t...
In this article, we present a novel redundancy scheme to realize a fault-tolerant IoT structure for application in high-reliability systems. The proposed fault-tolerant structure uses a centralized data fusion block a...
详细信息
Porcelain, as a significant cultural heritage, embodies the wisdom of human civilization. However, existing anti-counterfeiting and authentication technologies for porcelain are often unreliable and costly. This paper...
详细信息
暂无评论