Coursera Flash Sale
40% Off Coursera Plus for 3 Months!
Grab it
This talk explores the intersection of online learning and economics, focusing on how data-driven approaches can enhance economic models that traditionally rely on perfectly known random variables. Federico Fusco presents a comprehensive survey of recent research in online learning applications for economic scenarios, particularly in bidding, auction design, and bilateral trade. Learn about the exploration-exploitation tradeoff in economic contexts and how online learning frameworks can address the feedback challenges that emerge in real-world applications. The presentation examines technical challenges in designing effective learning algorithms and demonstrates methods for constructing "hard instances" to prove tightness results. The content draws from recent papers including "The Role of Transparency in Repeated First-Price Auctions with Unknown Valuations," "No-Regret Learning in Bilateral Trade via Global Budget Balance," and "Selling Joint Ads: A Regret Minimization Perspective." Delivered by Federico Fusco, Assistant Professor at Sapienza University of Rome, whose research spans Algorithmic Game Theory, Online Learning, and Submodular Maximization.
