Supervised Learning
Structured Prediction Theory Based on Factor Graph Complexity
Corinna Cortes, Vitaly Kuznetsov, Mehryar Mohri, Scott Yang
Neural Information Processing Systems http://nips.cc/
Active Nearest-Neighbor Learning in Metric Spaces
Aryeh Kontorovich, Sivan Sabato, Ruth Urner
We propose a pool-based non-parametric active learning algorithm for general metric spaces, called MArgin Regularized Metric Active Nearest Neighbor (MARMANN), which outputs a nearest-neighbor classifier. We give prediction error guarantees that depend on the noisy-margin properties of the input sample, and are competitive with those obtained by previously proposed passive learners. We prove that the label complexity of MARMANN is significantly lower than that of any passive learner with similar error guarantees. Our algorithm is based on a generalized sample compression scheme and a new label-efficient active model-selection procedure.
Improved Guarantees for Fully Dynamic k-Center Clustering with Outliers in General Metric Spaces
In the first case, points arrive sequentially, and only a summary can be stored in memory.
Geometry-Aware Adaptation for Pretrained Models
Machine learning models--including prominent zero-shot models--are often trained on datasets whose labels are only a small proportion of a larger label space. Such spaces are commonly equipped with a metric that relates the labels via distances between them.
Manifold Structured Prediction
Alessandro Rudi, Carlo Ciliberto, GianMaria Marconi, Lorenzo Rosasco
Neural Information Processing Systems http://nips.cc/
Learning latent variable structured prediction models with Gaussian perturbations
Neural Information Processing Systems http://nips.cc/
Model-Agnostic Private Learning
Raef Bassily, Abhradeep Guha Thakurta, Om Dipakbhai Thakkar
Neural Information Processing Systems http://nips.cc/
Nonparametric Contextual Bandits in Metric Spaces with Unknown Metric
Nirandika Wanigasekara, Christina Yu
Neural Information Processing Systems http://nips.cc/
