_id,title
11452,Distributed principal component analysis with limited communication
11453,Online learning of neural computations from sparse temporal feedback
11458,AC/DC: Alternating Compressed/DeCompressed training of deep neural networks
11463,M-FAC: Efficient matrix-free approximations of second-order information
11464,Towards tight communication lower bounds for distributed optimisation
14179,Self-supervised learning with data augmentations provably isolates content from style
14180,Dynamic inference with neural interpreters
14182,Backward-compatible prediction updates: A probabilistic approach
10593,PCA initialization for approximate message passing in rotationally invariant models
10594,When are solutions connected in deep networks?