Jun 14, 2019
We introduce a novel use of herding to address the problem of selecting samples from a large unlabeled dataset to efficiently evaluate the risk of a given model. Herding is an algorithm which elaborately draws samples to approximate the underlying distribution. We use herding to select the most informative samples and show that the loss evaluated on $k$ samples produced by herding converges to the expected loss at a rate $\mathcal{O}(1/k)$, which is much faster than $\mathcal{O}(1/\sqrt{k})$ for iid random sampling. We validate our analysis on both synthetic data and real data, and further explore the empirical performance of herding-based sampling in different cases of high-dimensional data.
The International Conference on Machine Learning (ICML) is the premier gathering of professionals dedicated to the advancement of the branch of artificial intelligence known as machine learning. ICML is globally renowned for presenting and publishing cutting-edge research on all aspects of machine learning used in closely related areas like artificial intelligence, statistics and data science, as well as important application areas such as machine vision, computational biology, speech recognition, and robotics. ICML is one of the fastest growing artificial intelligence conferences in the world. Participants at ICML span a wide range of backgrounds, from academic and industrial researchers, to entrepreneurs and engineers, to graduate students and postdocs.
Professional recording and live streaming, delivered globally.
Presentations on similar topic, category or speaker