93 citations · 215 across the 10 of their papers we have counts for
Showing 2020Show all
2 papers · 1 filter
stat.ML2020
Learning from eXtreme Bandit Feedback
Romain Lopez, Inderjit S. Dhillon, Michael I. Jordan
We study the problem of batch learning from bandit feedback in the setting of extremely large action spaces. Learning from extreme bandit feedback is ubiquitous in recommendation s…
stat.ML2020★ 23 cited
Decision-Making with Auto-Encoding Variational Bayes
Romain Lopez, Pierre Boyeau, Nir Yosef +2
To make decisions based on a model fit with auto-encoding variational Bayes (AEVB), practitioners often let the variational distribution serve as a surrogate for the posterior dist…