Showing cs.LGShow all
2 papers · 1 filter
cs.LG2022
Hypothesis Transfer in Bandits by Weighted Models
Steven Bilaj, Sofien Dhouib, Setareh Maghsudi
We consider the problem of contextual multi-armed bandits in the setting of hypothesis transfer learning. That is, we assume having access to a previously learned model on an unobs…
cs.LG2022
Connecting sufficient conditions for domain adaptation: source-guided uncertainty, relaxed divergences and discrepancy localization
Sofien Dhouib, Setareh Maghsudi
Recent advances in domain adaptation establish that requiring a low risk on the source domain and equal feature marginals degrade the adaptation's performance. At the same time, em…