A description of perturbation-based methods developed in machine learning to augment novel optimization methods with strong statistical guarantees. In nearly all machine learning, decisions must be made given current knowledge. Surprisingly, making what is believed to be the best decision is not always the best strategy, even when learning in a supervised learning setting. An emerging body of work on learning under different rules applies perturbations to decision and learning procedures. These methods provide simple and highly efficient learning rules with improved theoretical guarantees.…
Counted ratings come from accounts older than 7 days and were made on or after publication. Finished readers weigh ×1.0. Readers who have not finished yet weigh ×0.5. Did-not-finish ratings are shown but not counted.
