Acquiring and Aggregating Information in Societal Contexts

Subscribers:
344,000
Published on ● Video Link: https://www.youtube.com/watch?v=dKNWMAKHbtw



Category:
Guide
Duration: 58:33
1,295 views
13


The modern world is full of algorithms that use data to make decisions. The data often come from people; the predictions or decisions often affect people. Yet classically, the study of e.g. learning algorithms does not take into account the behavior or priorities of these participants. So: how does this "societal context" impact the understanding and design of systems that acquire and aggregate information?

This talk will discuss the design of systems that take into account, and indeed leverage, strategic behavior of participants in order to gather information and use it to make inferences, predictions, or decisions. We will break down the kinds of challenges and objectives that arise in these settings and several approaches for overcoming them using tools from game theory as well as machine learning.

See more at https://www.microsoft.com/en-us/research/video/acquiring-aggregating-information-societal-contexts/




Other Videos By Microsoft Research


2018-05-15Brokering Peace Talks in the Networking and Storage Arms Race with Dr. Anirudh Badam
2018-05-15Tiny Functions for Codecs, Compilation, and (maybe) soon Everything
2018-05-15Sparsity-aware Sound Field Capturing / Joint Source and Sensor Placement for Sound Field Control
2018-05-14Quantum Computing for Computer Scientists
2018-05-14Learning Optimal Interventions Under Uncertainty
2018-05-14Dynamic Matching in School Choice: Efficient Seat Reassignment after Late Cancellations
2018-05-12The Making of “Fungible Open Data” in Biomedical Research: Governance, Epistemic Trust, Public Good
2018-05-07Code in the Classroom with Dr. Peli de Halleux
2018-05-07Azure Accelerated Machine Learning with Project Brainwave
2018-05-07FPGAs in Microsoft's Intelligent Cloud
2018-04-30Acquiring and Aggregating Information in Societal Contexts
2018-04-30Connected Self-Ownership and Implications for Online Networks and Privacy Rights
2018-04-27Chakra: from Script to Optimized Code
2018-04-26Incentivizing Societal Contributions for and via Machine Learning
2018-04-25AI, Machine Learning, and the Reasoning Machine with Dr. Geoff Gordon
2018-04-23Haptic Controllers: How Microsoft is making virtual reality tangible
2018-04-23Accessibility - How Microsoft is making technology accessible to more people
2018-04-20Distill and transfer learning for robust multitask RL
2018-04-20Graph neural networks: Variations and applications
2018-04-20Active Mini-Batch Sampling using Repulsive Point Processes
2018-04-20Debiasing Evidence Approximations: Importance-Weighted Autoencoders Jackknife Variational Inference



Tags:
microsoft research