A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
Guarantees for tuning step size using meta-gradient descent.
MAML optimizes shared priors for subtasks in a nonconvex meta-objective.
Careful tuning of the learning rate, or even schedules thereof, can be crucial to effective neural net training. There has been much recent interest in gradient-based meta-optimization, where one tunes hyperparameters, or even learns an optimizer, in order to minimize the expected loss when the training procedure is un…
Meta-SAC automatically tunes SAC's entropy temperature for better exploration.
New method optimises learning via surrogate PAC-Bayes bounds.