TGIF: Data Science and Business

“TGIF” or “Think-Grapple-Innovate-Fridays” is a School of Data Science tradition. These events are an opportunity for Data Science team members to come together with potential collaborators to explore shared interests. Past TGIF events have focused on the arts, COVID research and police brutality. Check out below for our upcoming TGIF event!

Data Science & Business with Michael Albert

• The field of mechanism design has had significant success in constructing optimal mechanisms to allocate resources when there are information asymmetries. These successes include the modern second price auction format implemented by eBay as well as matching markets for medical residencies and kidney exchanges. However, there are many situations under which no optimal mechanism is known. For example, the revenue optimal mechanism for two bidders with two items is an open question. This has led to the adoption of black box non-linear function optimizers, such as deep neural networks, to learn good performing mechanisms. However, these learned mechanisms only approximately satisfy traditional mechanism design guarantees, such as incentive compatibility. Given that these mechanisms fail traditional mechanism design guarantees, they cannot guarantee any lower bound on their performance. In this work, we present a procedure where by having sample access to a mechanism we can prove a lower bound on the performance. Moreover, we develop new techniques to construct mechanisms using deep neural networks that provide good lower bounds on the performance.

• Join the call via Zoom. For the Zoom password, contact Danielle D'Andrea.