We will have our long-awaited student back-to-back talk after two years. It will be in-person and each talk takes 25 minutes including the Q&A. For this week we have:
Speaker: Jessie Finocchiaro, Harvard
Title: Designing convex surrogates for discrete prediction tasks via embeddings
Abstract: We formalize and study the natural approach of designing convex surrogate loss functions via embeddings, for problems such as classification, ranking, or structured prediction. In this...
Abstract: In most of the fair allocation literature about indivisible goods, the fairness constraint under consideration is between *all* pairs of agents. But this is often not representative of the real world, where we only typically care about (and get envious of) the people we actually know. This gives rise to a natural relaxation of many fair allocation problems, where we place agents...
SEC 1.413 & on Zoom here: https://harvard.zoom.us/j/97692964231?pwd=K05BMEhDNTZtbUhHYkZ5S21qZ2FKQT09#success
Calvin Li, formerly at Uber and the main architect behind their current surge pricing strategies. It will occur at the usual place and the usual time: this Friday, 6/3, at 1 pm ET, in SEC1.413 and streamed on zoom ...
Munyque Mittelmann will be presenting at the EconCS seminar meeting this Friday, 5/13, at 1 pm ET. The seminar will be held Zoom only,accessible at the usual link here. Hope to see you there :).
Ben Edelman (Harvard) will be presenting at the EconCS seminar meeting this Friday, 4/29, at 1 pm ET. The seminar will take place in the usual room, SEC1.413, and will also be streamed on zoom...
Elaine Shi will be presenting at the EconCS seminar meeting this Friday, 4/22, at 1 pm ET. The seminar will be held Zoom only,accessible at the usual link here. Hope to see you there :).
SEC 1.413 & on Zoom here: https://harvard.zoom.us/j/97692964231?pwd=K05BMEhDNTZtbUhHYkZ5S21qZ2FKQT09#success
Speaker: Gianluca Brero
Title: Automated Market Design via Reinforcement Learning
Abstract: In this talk, I will introduce the use of reinforcement learning to design algorithmic markets. First, I will show how (deep) reinforcement learning algorithms can be used to design sequential price mechanisms, where we can assume truthful agents’ behavior. I will then consider the more general class of mechanisms that combine a messaging round with a sequential-pricing...Read more about Automated Market Design via Reinforcement Learning
Yuqing Kong will be presenting at the EconCS seminar meeting this Friday, 3/25, at 1 pm ET. The seminar will be held Zoom only,accessible at the usual link here. Hope to see you there :).