Statistical Learning
Efficient Testable Learning of Halfspaces with Adversarial Label Noise
In the recently introduced testable learning model, one is required to produce a tester-learner such that if the data passes the tester, then one can trust the output of the robust learner on the data.
Replicable Clustering
This means that the algorithm designer needs to balance several conflicting desiderata.
ALIM: Adjusting Label Importance Mechanism for Noisy Partial Label Learning
Noisy partial label learning (noisy PLL) is an important branch of weakly supervised learning.
Neural Latent Geometry Search: Product Manifold Inference via Gromov-Hausdorff-Informed Bayesian Optimization Haitz Sáez de Ocáriz Borde Oxford Robotics Institute University of Oxford Álvaro Arroyo
Recent research indicates that the performance of machine learning models can be improved by aligning the geometry of the latent space with the underlying data structure.