Country
AutoPrune: AutomaticNetworkPruningby RegularizingAuxiliaryParameters
Tobuildabettergeneralized and easy-to-use pruning method, we propose AutoPrune, which prunes the network through optimizing a set of trainable auxiliary parameters instead of original weights.
Learning SMaLL Predictors
Vikas Garg, Ofer Dekel, Lin Xiao
Neural Information Processing Systems http://nips.cc/
Multivariate Stochastic Dominance via Optimal Transport and Applications to Models Benchmarking
Large Language Models that are evaluated on multiple metrics.
AnoShift: ADistributionShiftBenchmarkfor UnsupervisedAnomalyDetection
Theexisting benchmarks arefocused onsupervised learning, andtothe best of our knowledge, there is none for unsupervised learning.
DimensionalityReductionhasQuantifiable Imperfections: TwoGeometricBounds
Akeytechnical step inourproofsisaparticular optimizationproblem oftheL2-Wasserstein distance over a constrained set of distributions.
Twin Auxilary Classifiers GAN
Mingming Gong, Yanwu Xu, Chunyuan Li, Kun Zhang, Kayhan Batmanghelich
Neural Information Processing Systems http://nips.cc/
Imagine the Unseen World: A Benchmark for Systematic Generalization in Visual World Models
This work was partly done while C.G. was at Google DeepMind. C.G. is currently affiliated with EPFL.