BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:On the sample complexity of multi-objective learning - Fanny Yang 
 (ETH Zurich)
DTSTART:20251121T140000Z
DTEND:20251121T150000Z
UID:TALK237526@talks.cam.ac.uk
CONTACT:Qingyuan Zhao
DESCRIPTION:In multi-objective learning (MOL)\, several possibly competing
  prediction tasks must be solved jointly by a single model. Achieving good
  trade-offs may require a model class G with larger capacity than what is 
 necessary for solving the individual tasks. This\, in turn\, increases the
  statistical cost\, as reflected in known MOL bounds that depend on the co
 mplexity of G. We show that this cost is unavoidable for some losses\, eve
 n in an idealized semi-supervised setting\, where the learner has access t
 o the Bayes-optimal solutions for the individual tasks as well as the marg
 inal distributions over the covariates. On the other hand\, for objectives
  defined with Bregman losses\, we prove that the complexity of G may come 
 into play only in terms of unlabeled data. Concretely\, we establish sampl
 e complexity upper bounds\, showing precisely when and how unlabeled data 
 can significantly alleviate the need for labeled data. These rates are ach
 ieved by a simple\, semi-supervised algorithm via pseudo-labeling.
LOCATION:MR12\, Centre for Mathematical Sciences
END:VEVENT
END:VCALENDAR