MargCTGAN: A “Marginally” Better CTGAN for the Low Sample Regime

Record type:

paperposter

MargCTGAN: A “Marginally” Better CTGAN for the Low Sample Regime

Poster presented at the Deep Learning Indaba 2023 by Tejumade Afonja

Visit

storage.googleapis.com

Tags

poster deep learning indaba 2023 deep learning indaba dli

Similar

Complexity boosted adaptive training for better low resource ASR performanceMarginally interpretable spatial logistic regression with bridge processesHybrid Training Strategies for Low-Resource Cross-Lingual NER Sample EfficiencyXAL: EXplainable Active Learning Makes Classifiers Better Low-resource LearnersBetter as Generators Than Classifiers: Leveraging LLMs and Synthetic Data for Low-Resource Multilingual ClassificationExchange rate regime verification: an alternative method of testing for regime changes

Complexity boosted adaptive training for better low resource ASR performance

During the entire training process of the ASR model, the intensity of data augmentation and the appr

Marginally interpretable spatial logistic regression with bridge processes

In including random effects to account for dependent observations, the odds ratio interpretation of

Hybrid Training Strategies for Low-Resource Cross-Lingual NER Sample Efficiency

Cross-lingual Named Entity Recognition (NER) leverages knowledge transfer between languages to ident

XAL: EXplainable Active Learning Makes Classifiers Better Low-resource Learners

Active learning (AL), which aims to construct an effective training set by iteratively curating the

Better as Generators Than Classifiers: Leveraging LLMs and Synthetic Data for Low-Resource Multilingual Classification

Large Language Models (LLMs) have demonstrated remarkable multilingual capabilities, making them pro

Exchange rate regime verification: an alternative method of testing for regime changes

This work proposes a change in persistence test for identifying de facto exchange rate regime change