{"689967":{"#nid":"689967","#data":{"type":"event","title":"PhD Defense by Yifan Wang","body":[{"value":"\u003Cp\u003E\u003Cstrong\u003EPresentation details\u003C\/strong\u003E:\u003C\/p\u003E\u003Cp\u003ETitle: Learning to Price with Limited Information\u003C\/p\u003E\u003Cp\u003EDate: May 5th, 2026\u003C\/p\u003E\u003Cp\u003ETime: 10:00 AM \u2013 12:00 PM ET\u003C\/p\u003E\u003Cp\u003ELocation: KACB 3100 (\u003Ca href=\u0022https:\/\/nam12.safelinks.protection.outlook.com\/?url=https%3A%2F%2Fgatech.zoom.us%2Fj%2F99377659191%3Fpwd%3DjszsCCSSRFsLluWrp9z0IJTZby8lmq.1\u0026amp;data=05%7C02%7Ctm186%40gtvault.onmicrosoft.com%7C635909f64a1b4869eeb508dea1384a07%7C482198bbae7b4b258b7a6d7f32faa083%7C1%7C0%7C639125460317777867%7CUnknown%7CTWFpbGZsb3d8eyJFbXB0eU1hcGkiOnRydWUsIlYiOiIwLjAuMDAwMCIsIlAiOiJXaW4zMiIsIkFOIjoiTWFpbCIsIldUIjoyfQ%3D%3D%7C0%7C%7C%7C\u0026amp;sdata=pRbaE6MT4UgtJyR%2Fr5zpFpo%2F7T4j1PD0zEeqQdfqud8%3D\u0026amp;reserved=0\u0022 title=\u0022https:\/\/gatech.zoom.us\/j\/99377659191?pwd=jszsCCSSRFsLluWrp9z0IJTZby8lmq.1\u0022\u003EZoom link\u003C\/a\u003E)\u003C\/p\u003E\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003ECommittee\u003C\/strong\u003E:\u003C\/p\u003E\u003Cp\u003EProf. Sahil Singla (Advisor), School of Computer Science, Georgia Institute of Technology\u003C\/p\u003E\u003Cp\u003EProf. Jan van den Brand, School of Computer Science, Georgia Institute of Technology\u003C\/p\u003E\u003Cp\u003EProf. Santosh Vempala, School of Computer Science, Georgia Institute of Technology\u003C\/p\u003E\u003Cp\u003EProf. Will Ma, Graduate School of Business and Data Science Institute, Columbia University\u003C\/p\u003E\u003Cp\u003EProf. Rad Niazadeh, Booth School of Business, University of Chicago\u003C\/p\u003E\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EAbstract\u003C\/strong\u003E:\u003C\/p\u003E\u003Cp\u003EResource allocation is a central problem in theoretical computer science, operations research, and economics. In a resource allocation problem, a platform must design efficient algorithms to assign limited resources to participating agents under uncertainty, aiming to maximize either the total social welfare or the total revenue.\u003C\/p\u003E\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EAmong the various algorithms for resource allocation, pricing algorithms are one of the most common ways to distribute resources due to its simplicity. Theoretically, pricing algorithms can be modeled as a system in which a platform sets prices for resources, while participating agents with valuations drawn from underlying distributions make greedy decisions with respect to the prices. However, these distributions are typically unknown to the platform and must therefore be learned, either from limited offline data or through real-time interactions with agents.\u003C\/p\u003E\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\u003Cp\u003ETraditional approaches to learning in pricing algorithms often assume access to a large number of samples from each agent. In many real-world markets, however, the available information is sparse, noisy, or indirect. This raises a fundamental question: how can we learn effective pricing algorithms under such limited information constraints?\u003C\/p\u003E\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EIn this thesis, I address this question by studying the learnability of resource allocation algorithms under three highly restrictive information models:\u003C\/p\u003E\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E1. Learning from a single sample, where the platform has access to only one sample from each agent\u2019s distribution.\u003C\/p\u003E\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E2. Learning from pricing queries, where the platform can only post prices and observe agents\u2019 decisions as feedback.\u003C\/p\u003E\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E3. Online learning with limited feedback, where the platform needs to adjust the algorithm dynamically with limited feedback.\u003C\/p\u003E\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EI will demonstrate how pricing algorithms can be successfully learned under these frameworks. Together, these results provide a unified perspective on learning pricing algorithms under limited information, and show that strong performance guarantees are attainable even in highly information-constrained environments.\u003C\/p\u003E\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E","summary":"","format":"limited_html"}],"field_subtitle":"","field_summary":[{"value":"\u003Cp\u003ELearning to Price with Limited Information\u003C\/p\u003E","format":"limited_html"}],"field_summary_sentence":[{"value":"Learning to Price with Limited Information"}],"uid":"27707","created_gmt":"2026-04-23 13:49:37","changed_gmt":"2026-04-23 13:50:13","author":"Tatianna Richardson","boilerplate_text":"","field_publication":"","field_article_url":"","field_event_time":{"event_time_start":"2026-05-05T10:00:07-04:00","event_time_end":"2026-05-05T12:00:00-04:00","event_time_end_last":"2026-05-05T12:00:00-04:00","gmt_time_start":"2026-05-05 14:00:07","gmt_time_end":"2026-05-05 16:00:00","gmt_time_end_last":"2026-05-05 16:00:00","rrule":null,"timezone":"America\/New_York"},"location":"KACB 3100 (Zoom link)","extras":[],"groups":[{"id":"221981","name":"Graduate Studies"}],"categories":[],"keywords":[{"id":"100811","name":"Phd Defense"}],"core_research_areas":[],"news_room_topics":[],"event_categories":[{"id":"1788","name":"Other\/Miscellaneous"}],"invited_audience":[{"id":"78771","name":"Public"}],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[],"email":[],"slides":[],"orientation":[],"userdata":""}}}