Bayesmix: Sharp Loss Bounds M. Hutter (on my SNF grant; IJFCS / ECML / ICML 2001)

• µ(x) unknown

• Predict k-th symbol: loss in [0,1].

• Optimal: minimize µ-expected loss

• Instead: minimize M-expected loss

• Total loss difference for first n symbols:

• If µ deterministic then soon no more errors!

Previous slide

Next slide

Back to first slide

View graphic version