114.02.27演講公告
資工系專題演講(Lecture)
日期(date)/時間(time)：114年2月27日(四/Thu)13:10~15:00
地點(location)：電綜大樓B107教室
演講者(speaker)：陳柏安 副教授兼所長
服務單位(job)：國立陽明交通大學資訊管理研究所
講題(topic)：Multiagent learning for competitive opinion optimization
摘要(summary)：
From a perspective of designing or engineering for opinion formation games in social networks, the opinion maximization (or minimization) problem has been studied mainly for designing seeding algorithms that aim at selecting a subset of nodes to control their opinions. We first define a two-player zero-sum Stackelberg game of competitive opinion optimization by letting the player under study as the leader minimize the sum of expressed opinions by doing so-called “internal opinion design”, knowing that the other adversarial player as the follower is to maximize the same objective by also conducting her own internal opinion design. We furthermore consider multiagent learning, specifically using the Optimistic Gradient Descent Ascent, and analyze its convergence to equilibria in the simultaneous-game version of competitive opinion optimization.
（This is a joint work with Chi-Jen Lu, Chuang-Chieh Lin, An-Tzu Teng, and Ke-Wei Fu, published in Theoretical Computer Science, Nov 2024.)
與工程認證核心能力關聯性：
■ 培養持續學習與獨立學習的習慣與能力
日期(date)/時間(time)：114年2月27日(四/Thu)13:10~15:00
地點(location)：電綜大樓B107教室
演講者(speaker)：陳柏安 副教授兼所長
服務單位(job)：國立陽明交通大學資訊管理研究所
講題(topic)：Multiagent learning for competitive opinion optimization
摘要(summary)：
From a perspective of designing or engineering for opinion formation games in social networks, the opinion maximization (or minimization) problem has been studied mainly for designing seeding algorithms that aim at selecting a subset of nodes to control their opinions. We first define a two-player zero-sum Stackelberg game of competitive opinion optimization by letting the player under study as the leader minimize the sum of expressed opinions by doing so-called “internal opinion design”, knowing that the other adversarial player as the follower is to maximize the same objective by also conducting her own internal opinion design. We furthermore consider multiagent learning, specifically using the Optimistic Gradient Descent Ascent, and analyze its convergence to equilibria in the simultaneous-game version of competitive opinion optimization.
（This is a joint work with Chi-Jen Lu, Chuang-Chieh Lin, An-Tzu Teng, and Ke-Wei Fu, published in Theoretical Computer Science, Nov 2024.)
與工程認證核心能力關聯性：
■ 培養持續學習與獨立學習的習慣與能力