Variance Constrained Distribution Alignment in Few-shot Models

Xiaohong Cai, Yi SUN, Zhaowen Lin, Tianwei Cai
Proceedings of The 29th International Conference on Artificial Intelligence and Statistics, PMLR 300:757-765, 2026.

Abstract

Learning generative models from the limited samples remains challenging due to unstable estimation of class conditional representations. Such instability often leads to intra-class distribution drift and degraded generalization under few sample regimes. To address these challenges, we propose a method that can model class level latent distributions for flexible and efficient few shot synthesis. Specifically, each input is represented by a learnable conditional latent distribution. Metric based statistical modeling effectively disentangles latent variables, contracts intra-class variance, and enlarges inter-class margins while enforcing cross task distributional alignment. Furthermore, we provide a variance based generalization analysis, showing that controlling class conditional variance tightens generalization bounds under few sample regimes. Experiments on the benchmark datasets demonstrate that our method surpasses prior works in visual quality and diversity, highlighting the benefit of statistical alignment for robust few shot generative modeling.

Cite this Paper

BibTeX
@InProceedings{pmlr-v300-cai26a, title = { Variance Constrained Distribution Alignment in Few-shot Models }, author = {Cai, Xiaohong and SUN, Yi and Lin, Zhaowen and Cai, Tianwei}, booktitle = {Proceedings of The 29th International Conference on Artificial Intelligence and Statistics}, pages = {757--765}, year = {2026}, editor = {Khan, Emtiyaz and Li, Yingzhen and Solin, Arno and Ramdas, Aaditya}, volume = {300}, series = {Proceedings of Machine Learning Research}, month = {02--05 May}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v300/main/assets/cai26a/cai26a.pdf}, url = {https://proceedings.mlr.press/v300/cai26a.html}, abstract = { Learning generative models from the limited samples remains challenging due to unstable estimation of class conditional representations. Such instability often leads to intra-class distribution drift and degraded generalization under few sample regimes. To address these challenges, we propose a method that can model class level latent distributions for flexible and efficient few shot synthesis. Specifically, each input is represented by a learnable conditional latent distribution. Metric based statistical modeling effectively disentangles latent variables, contracts intra-class variance, and enlarges inter-class margins while enforcing cross task distributional alignment. Furthermore, we provide a variance based generalization analysis, showing that controlling class conditional variance tightens generalization bounds under few sample regimes. Experiments on the benchmark datasets demonstrate that our method surpasses prior works in visual quality and diversity, highlighting the benefit of statistical alignment for robust few shot generative modeling. } }
Endnote
%0 Conference Paper %T Variance Constrained Distribution Alignment in Few-shot Models %A Xiaohong Cai %A Yi SUN %A Zhaowen Lin %A Tianwei Cai %B Proceedings of The 29th International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2026 %E Emtiyaz Khan %E Yingzhen Li %E Arno Solin %E Aaditya Ramdas %F pmlr-v300-cai26a %I PMLR %P 757--765 %U https://proceedings.mlr.press/v300/cai26a.html %V 300 %X Learning generative models from the limited samples remains challenging due to unstable estimation of class conditional representations. Such instability often leads to intra-class distribution drift and degraded generalization under few sample regimes. To address these challenges, we propose a method that can model class level latent distributions for flexible and efficient few shot synthesis. Specifically, each input is represented by a learnable conditional latent distribution. Metric based statistical modeling effectively disentangles latent variables, contracts intra-class variance, and enlarges inter-class margins while enforcing cross task distributional alignment. Furthermore, we provide a variance based generalization analysis, showing that controlling class conditional variance tightens generalization bounds under few sample regimes. Experiments on the benchmark datasets demonstrate that our method surpasses prior works in visual quality and diversity, highlighting the benefit of statistical alignment for robust few shot generative modeling.
APA
Cai, X., SUN, Y., Lin, Z. & Cai, T.. (2026). Variance Constrained Distribution Alignment in Few-shot Models . Proceedings of The 29th International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 300:757-765 Available from https://proceedings.mlr.press/v300/cai26a.html.

Related Material