Uncategorized

Tiered Architectures, Counterfactual Learning, and Sample Complexity

FavoriteLoadingAdd to favorites

I’m on a product team now, and once again I find myself working on a tiered architecture: an “L1” model selects some candidates which are passed to an “L2” model which reranks and filters the candidates which are passed to an “L3”, etc. The motivation for this is typically computational, e.g., you can index a DSSM model pretty easily but indexing a BIDAF model is more challenging. However I think there are potential sample complexity benefits as well.I worry about sample complexity in counterfactual setups, because I think it is the likely next source for AI winter. Reinforcement learning takes a tremendous amount of data to converge, which is why all the spectacular results from the media are in simulated environments, self-play scenarios, discrete optimization of a sub-component within a fully supervised setting, or other situations where there is essentially…
Original Post: Tiered Architectures, Counterfactual Learning, and Sample Complexity