The success of deep learning requires large datasets and extensive training, which can create significant computational challenges. To address these challenges, pseudo-coresets, small learnable datasets that mimic the entire data, have been proposed. Bayesian Neural Networks, which offer predictive uncertainty and probabilistic interpretation for deep neural networks, also face issues with large-scale datasets due to their high-dimensional parameter space. Prior works on Bayesian Pseudo-Coresets (BPC) attempt to reduce the computational load for computing weight posterior distribution by a small number of pseudo-coresets but suffer from memory inefficiency during BPC training and sub-optimal results. To overcome these limitations, we propose Variational Bayesian Pseudo-Coreset (VBPC), a novel approach that utilizes variational inference to efficiently approximate the posterior distribution, reducing memory usage and computational costs while improving performance across benchmark datasets.
View on arXiv@article{lee2025_2502.21143,
title={ Variational Bayesian Pseudo-Coreset },
author={ Hyungi Lee and Seungyoo Lee and Juho Lee },
journal={arXiv preprint arXiv:2502.21143},
year={ 2025 }
}