12 citations · 14 across the 5 of their papers we have counts for
5 papers · 1 filter
Towards Understanding Epoch-wise Double descent in Two-layer Linear Neural Networks
Amanda Olmin, Fredrik Lindsten
Epoch-wise double descent is the phenomenon where generalisation performance improves beyond the point of overfitting, resulting in a generalisation curve exhibiting two descents u…
On the connection between Noise-Contrastive Estimation and Contrastive Divergence
Amanda Olmin, Jakob Lindqvist, Lennart Svensson +1
Noise-contrastive estimation (NCE) is a popular method for estimating unnormalised probabilistic models, such as energy-based models, which are effective for modelling complex data…
Active Learning with Weak Supervision for Gaussian Processes
Amanda Olmin, Jakob Lindqvist, Lennart Svensson +1
Annotating data for supervised learning can be costly. When the annotation budget is limited, active learning can be used to select and annotate those observations that are likely…
Robustness and Reliability When Training With Noisy Labels
Amanda Olmin, Fredrik Lindsten
Labelling of data for supervised learning can be costly and time-consuming and the risk of incorporating label noise in large data sets is imminent. When training a flexible discri…
A general framework for ensemble distribution distillation
Jakob Lindqvist, Amanda Olmin, Fredrik Lindsten +1
Ensembles of neural networks have been shown to give better performance than single networks, both in terms of predictions and uncertainty estimation. Additionally, ensembles allow…