2023
No-Regret Learning with Unbounded Losses: The Case of Logarithmic Pooling
NeurIPS 2023poster
For each of $T$ time steps, $m$ experts report probability distributions over $n$ outcomes; we wish to learn to aggregate these forecasts in a way that attains a no-regret guarantee. We focus on the fundamental and practical aggregation method known as *logarithmic pooling* -- a weighted average of…