Moran
PulseAugur coverage of Moran — every cluster mentioning Moran across labs, papers, and developer communities, ranked by signal.
-
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 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…
-
Researchers explore credit attribution challenges for generative AI models
Researchers have identified significant challenges in enabling autoregressive generative AI models to properly attribute credit to their training data. A new paper explores the concept of Counterfactual Credit Attributi…