✳flâneur — a map of the web's best reading

To Understand Language is to Understand Generalization | Eric Jang

evjang.com · 2,835 words · saved by 4 readers

In my essay “Just ask for Generalization”, I argued that some optimization capabilities, such as reinforcement learning from sub-optimal trajectories, might be better implemented by generalization than by construction. We have to generalize to unseen situations at deployment time anyway, so why not focus on generalization capability as the first class citizen, and then “just ask for optimality” as an unseen case? A corollary to this design philosophy is that we should discard inductive biases that introduce optimization bottlenecks for “the data sponge”: if an inductive bias turns out to be merely “data in disguise”, it may not only cease to provide a benefit in the high data regime, but actually hinder the model on examples where the inductive bias no longer applies.

In my essay "Just ask for Generalization" , I argued that some optimization capabilities, such as reinforcement learning from sub-optimal trajectories, might be better implemented by generalization than by construction . We have to generalize to unseen situations at deployment time anyway, so why not focus on generalization capability as the first class citizen, and then "just ask for optimality" as an unseen case? A corollary to this design philosophy is that we should discard inductive biases that introduce optimization bottlenecks for "the data sponge": if an inductive bias turns out to be

Explore this link on the map →

saved by

related reading