activity
20162022
most citedImproving the Expected Improvement Algorithm

39 citations · 154 across the 26 of their papers we have counts for

collaborators
Showing 2020Show all

9 papers · 1 filter

stat.ML20202 cited

Open Set Domain Adaptation by Extreme Value Theory

Yiming Xu, Diego Klabjan

Common domain adaptation techniques assume that the source domain and the target domain share an identical label space, which is problematic since when target samples are unlabeled…

cs.AI2020

Concept Drift and Covariate Shift Detection Ensemble with Lagged Labels

Yiming Xu, Diego Klabjan

In model serving, having one fixed model during the entire often life-long inference process is usually detrimental to model performance, as data distribution evolves over time, re…

cs.LG20201 cited

Inverse Classification with Limited Budget and Maximum Number of Perturbed Samples

Jaehoon Koo, Diego Klabjan, Jean Utke

Most recent machine learning research focuses on developing new classifiers for the sake of improving classification accuracy. With many well-performing state-of-the-art classifier…

cs.LG20204 cited

Efficient Architecture Search for Continual Learning

Qiang Gao, Zhipeng Luo, Diego Klabjan

Continual learning with neural networks is an important learning framework in AI that aims to learn a sequence of tasks well. However, it is often confronted with three challenges:…

cs.LG2020

Open-Set Recognition with Gaussian Mixture Variational Autoencoders

Alexander Cao, Yuan Luo, Diego Klabjan

In inference, open-set classification is to either classify a sample into a known class from training or reject it as an unknown class. Existing deep open-set classifiers train exp…

cs.LG20206 cited

Neural Network Retraining for Model Serving

Diego Klabjan, Xiaofeng Zhu

We propose incremental (re)training of a neural network model to cope with a continuous flow of new data in inference during model serving. As such, this is a life-long learning pr…