Filters








2 Hits in 2.0 sec

NeuMiss networks: differentiable programming for supervised learning with missing values [article]

Marine Le Morvan
2020 arXiv   pre-print
The presence of missing values makes supervised learning much more challenging.  ...  We provide an upper bound on the Bayes risk of NeuMiss networks, and show that they have good predictive accuracy with both a number of parameters and a computational complexity independent of the number  ...  Supplementary materials -NeuMiss networks: differentiable programming for supervised learning with missing values Then the product f (X)g(X) is another gaussian function given by: f (X)g(X) = exp − 1 2  ... 
arXiv:2007.01627v4 fatcat:ctkipqw3dje27hul6rla7ty7xe

Gradient Importance Learning for Incomplete Observations [article]

Qitong Gao, Dong Wang, Joshua D. Amason, Siyang Yuan, Chenyang Tao, Ricardo Henao, Majda Hadziahmetovic, Lawrence Carin, Miroslav Pajic
2022 arXiv   pre-print
missing values without imputation.  ...  with real-world applications and could suffer from poor performance in subsequent tasks such as classification.  ...  Neumiss networks: differentiable programming for supervised learning with missing val- ues. In NeurIPS, 2020.  ... 
arXiv:2107.01983v4 fatcat:qumjhvlnlvh4bbeztrijfurlqi