Deep Learning
Analytic Insights into Structure and Rank of Neural Network Hessian Maps Sidak Pal Singh
This yields exact formulas and tight upper bounds for the Hessian rank of deep linear networks -- allowing for an elegant interpretation in terms of rank deficiency. Moreover, we demonstrate that our bounds remain faithful as an estimate of the numerical Hessian rank, for a larger class of models such as rectified and hyperbolic tangent networks.
SketchBoost: Fast Gradient Boosted Decision Tree for Multioutput Problems
Although there are highly effective GBDT implementations, their scalability to such problems is still unsatisfactory.
Not All Unlabeled Data are Equal: Learning to Weight Data in Semi-supervised Learning Zhongzheng Ren
But not all unlabeled data are equal. In this paper we study how to use a different weight for every unlabeled example. Manual tuning of all those weights - as done in prior work - is no longer possible.
Benchopt: Reproducible, efficient and collaborative optimization benchmarks
Numerical experiments have become an essential part of statistics and machine learning (ML).
A Appendix
In this supplementary material, we first provide detailed network architectures in Sec. Then details of metrics utilized in our experiments are demonstrated in Sec. We give more implementation details in Sec. We further introduce our utilized datasets in Sec. A.5. Limitations and broader impact are then discussed in Sec.
