Hanneke
PulseAugur coverage of Hanneke — every cluster mentioning Hanneke across labs, papers, and developer communities, ranked by signal.
-
Researchers find exponential gap in AI learning complexity between deterministic and randomized methods
Researchers have identified an exponential gap in the complexity of online learning between deterministic and randomized approaches when dealing with thresholds on an unknown order. A study by Attias, Hanneke, and Ramas…
-
Two papers resolve open problems in weighted data selection for linear regression
Two new papers published on arXiv address open problems in weighted data selection for linear regression. The first paper resolves a threshold question posed at COLT 2025, proving that $(m+1)d$ weighted examples are exa…
-
New Algorithm Boosts Adversarial Robustness in Learning Models
Researchers have developed a new algorithm that significantly improves the ability to learn predictors robust to adversarial examples. This method achieves linear sample complexity in the VC dimension, an exponential im…
-
New research decouples single-instance learning rates from direct-sum rates
A new research paper by Hanneke, Moran, and Waknine explores the relationship between agnostic PAC learning curves and direct sums in machine learning. The study demonstrates that the learning rate of a single instance …
-
New VC dimension bounds for partial concept classes in L_p spaces
Researchers have extended the concept of VC dimension to partial functions, specifically focusing on geometric partial concept classes (PCCs) in real Banach spaces. They established dimension-free upper bounds for the V…
-
New research proves optimal sample complexity for multiclass learning
Researchers have resolved a long-standing question regarding the optimal sample complexity for multiclass classification problems. Their work establishes a connection between the DS dimension and hypergraph density, pro…