Oceania
Multilabel reductions: what is my loss optimising?
Aditya K. Menon, Ankit Singh Rawat, Sashank Reddi, Sanjiv Kumar
Neural Information Processing Systems http://nips.cc/
Automated Classification of Model Errors on ImageNet
While the ImageNet dataset has been driving computer vision research over the past decade, significant label noise and ambiguity have made top-1 accuracy an insufficient measure of further progress.
Initialization of ReLUs for Dynamical Isometry
Rebekka Burkholz, Alina Dubatovka
Neural Information Processing Systems http://nips.cc/
Cooperative Learning of Audio and Video Models from Self-Supervised Synchronization
Bruno Korbar, Du Tran, Lorenzo Torresani
Toeasethelearning, wedemonstrate thatitisbeneficial toadoptacurriculum learning strategy [23], where harder negatives are introduced after an initial stage of learning on easiernegatives.
Sublinear Time Low-Rank Approximation of Distance Matrices
In an attempt to reduce their description size, we study low rank approximation of such matrices.
The Learnability of In-Context Learning
Our theoretical analysis reveals that in this setting, in-context learning is more about identifying the task than about learning it, a result which is in line with a series of recent empirical findings.
A Universally Optimal Multistage Accelerated Stochastic Gradient Method
Necdet Serhat Aybat, Alireza Fallah, Mert Gurbuzbalaban, Asuman Ozdaglar
Neural Information Processing Systems http://nips.cc/
Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNs
Timur Garipov, Pavel Izmailov, Dmitrii Podoprikhin, Dmitry P. Vetrov, Andrew G. Wilson
The loss functions of deep neural networks are complex and their geometric properties are not well understood.
