NeurIPS 2022

Structured Recognition for Generative Models with Explaining Away
Changmin Yu, Hugo Soulat, Neil Burgess, Maneesh Sahani
https://arxiv.org/abs/2209.05212

KSD Aggregated Goodness-of-fit Test
Antonin Schrab, Benjamin Guedj, Arthur Gretton
https://arxiv.org/abs/2202.00824

Computationally Efficient Aggregated Kernel Tests using Incomplete U-statistics
Antonin Schrab, Ilmun Kim, Benjamin Guedj, Arthur Gretton
https://arxiv.org/abs/2206.09194

Optimal Rates for Regularized Conditional Mean Embedding Learning
Zhu Li*, Dimitri Meunier*, Mattes Mollenhauer, Arthur Gretton
https://arxiv.org/abs/2208.01711

Exact Learning Dynamics of Deep Linear Networks with Prior Knowledge
Clémentine Carla Juliette Dominé, Lukas Braun, James E Fitzgerald, Andrew M Saxe
(OpenReview link)

Data Distributional Properties Drive Emergent In-Context Learning in Transformers
Stephanie C.Y. Chan, Adam Santoro, Andrew K. Lampinen, Jane X. Wang, Aaditya Singh, Pierre H. Richemond, Jay McClelland, Felix Hill
https://arxiv.org/abs/2205.05055

Stability and Scalability of Node Perturbation Learning
Naoki Hiratani, Yash Mehta, Tim Lillicrap, Peter Latham
(OpenReview link)

An Analytical Theory of Curriculum Learning in Teacher-Student Networks
Luca Saglietti, Stefano Mannelli, Andrew Saxe
https://arxiv.org/abs/2106.08068