Statistical Learning
Practical Sharpness-Aware Minimization Cannot Converge All the Way to Optima
To address this gap, we study deterministic/stochastic versions of SAM with practical configurations (i.e., constant
Domain Generalization via Model-Agnostic Learning of Semantic Features
Qi Dou, Daniel Coelho de Castro, Konstantinos Kamnitsas, Ben Glocker
Further, we introduce two complementary losses which explicitly regularize the semantic structure of thefeature space.
Locality-Sensitive Hashing for f-Divergences: Mutual Information Loss and Beyond
Lin Chen, Hossein Esfandiari, Gang Fu, Vahab Mirrokni
Neural Information Processing Systems http://nips.cc/
Shaping the distribution of neural responses with interneurons in a recurrent circuit model
Neural circuits are typically comprised of populations of primary (excitatory) neurons and local (inhibitory) interneurons.
Random Projections and Sampling Algorithms for Clustering of High-Dimensional Polygonal Curves
Stefan Meintrup, Alexander Munteanu, Dennis Rohde
Neural Information Processing Systems http://nips.cc/