Is there anything afuture user could do to mitigate theseundesirableharms? Although ConfLab's long-term vision is towards developing technology to assist individuals in navigating social interactions, the data could also affect a community in unintended ways: for instance, cause worsened social satisfaction, alackofagency,stereotype newcomers andveterans, or benefit only those members of the community who make use of resulting applications at the expense of the rest. More nefarious uses involve exploiting the data for developing methods that harmfully surveilorprofile people.

Ourbenchmarks showcase some of the open research tasks related to in-the-wild privacy-preserving social data analysis: keypoints detection from overhead camera views, skeleton-based no-audiospeakerdetection,andF-formationdetection.

We study minimax optimal reinforcement learning in episodic factored Markov decision processes (FMDPs), which are MDPs with conditionally independent transition components.

Modern deep neural networks, while strong in many domains [29], have notmastered comparable language-basedgeneralization challenges, afactconjectured tounderlie their sample inefficiencyand inflexibility [26,25,8].