1 citations · 4 across the 17 of their papers we have counts for
Showing 2026 · math.STShow all
2 papers · 2 filters
math.ST2026
Reconciling Universal and Uniform Learning with -Aggregation
Mikael Møller Høgsgaard, Patrick Rebeschini, Tobias Wegel
We study regression under bounded responses in terms of excess mean squared error. When the comparator class is finite, this setting is known as model selection aggregation, and ac…
math.ST2026
Aggregation with Exponential Weights is Optimal in Expectation
Mikael Møller Høgsgaard, Patrick Rebeschini, Tobias Wegel
The aggregation with exponential weights (AEW) estimator is not fully understood in the basic setting of model selection aggregation with squared loss. In particular, whether it is…