Technology
ClimbQ: Class Imbalanced Quantization Enabling Robustness on Efficient Inferences Ting-An Chen 1,2, De-Nian Y ang 2,3 Ming-Syan Chen 1,3 1
Despite a realistic problem, quantization on class-imbalanced data has not been studied.
Causal Effect Identification in a Sub-Population with Latent Variables Amir Mohammad Abouei
Causal inference, i.e., understanding the effect of an intervention in a stochastic system, is a key focus of research in statistics and machine learning [
Change-pointDetectionforSparseandDense FunctionalDatainGeneralDimensions
We study the problem of change-point detection and localisation for functional data sequentially observed on a generald-dimensional space, where we allow thefunctional curvestobeeither sparsely ordensely sampled.
Gamma-Poisson Dynamic Matrix Factorization Embedded with Metadata Influence
Trong Dinh Thac Do, Longbing Cao
Neural Information Processing Systems http://nips.cc/
GENO -- GENeric Optimization for Classical Machine Learning
Soeren Laue, Matthias Mitterreiter, Joachim Giesen
Neural Information Processing Systems http://nips.cc/
Appendix 465 Table of Contents
The Appendix is organized as follows.
Actively Testing Y our Model While It Learns: Realizing Label-Efficient Learning in Practice Dayou Yu
In active learning (AL), we focus on reducing the data annotation cost from the model training perspective. However, "testing", which often refers to the model
On Single Source Robustness in Deep Fusion Models
One natural way of improving a model's performance is to make use of multiple input sources relevant to a given task so that enough information can be extracted to build strong features.
