Improving Generalization via Meta-Learning on Hard Samples

arXiv:2403.12236v1 Announce Type: new
Abstract: Learned reweighting (LRW) approaches to supervised learning use an optimization criterion to assign weights for training instances, in order to maximize performance on a representative validation dataset. We pose and formalize the problem of optimized selection of the validation set used in LRW training, to improve classifier generalization. In particular, we show that using hard-to-classify instances in the validation set has both a theoretical connection to, and strong empirical evidence of generalization. We provide an …

abstract arxiv classifier criterion cs.cv cs.lg dataset instances meta meta-learning optimization performance samples set supervised learning training type validation via