Europe
2 Background
Inprinciple, onecandesign Lipschitz constrained architectures using the composition property of Lipschitz functions, but Anil et al.[2] recently identified a key obstacle to this approach: gradient norm attenuation.
Minimax Regret for Cascading Bandits
Cascading bandits is a natural and popular model that frames the task of learning to rank from Bernoulli click feedback in a bandit setting.
Byzantine Robustness and Partial Participation Can Be Achieved at Once: Just Clip Gradient Differences
In our work, we propose the first distributed method with client sampling and provable tolerance to Byzantine workers.
Accurate Uncertainty Estimation and Decomposition in Ensemble Learning
Jeremiah Liu, John Paisley, Marianthi-Anna Kioumourtzoglou, Brent Coull
Neural Information Processing Systems http://nips.cc/
Rule Extrapolation in Language Models: A Study of Compositional Generalization on OOD Prompts Anna Mészáros
LLMs show remarkable emergent abilities, such as inferring concepts from presumably out-of-distribution prompts, known as in-context learning.
