Scalable and Efficient Probabilistic Inference for Bayesian Deep Learning and Generative Modeling
Abstract
Probabilistic inference is a fundamental challenge in machine learning, spanning tasks from approximate Bayesian inference to generative AI. In this talk, I will present theoretically-guaranteed scalable and efficient probabilistic inference with applications in Bayesian deep learning and generative modeling. First, I will introduce a new compute paradigm for probabilistic inference that leverages modern accelerators, specifically low-precision and sparsity, to significantly speed up inference while preserving accuracy. Next, I will present a new framework for efficient inference in discrete domains, utilizing gradient information—a largely overlooked feature of discrete distributions—to enable more informed and directional exploration. Finally, I will showcase experimental results demonstrating the effectiveness of these methods across various ML tasks, including Bayesian neural networks, energy-based models, and large language models.
BibTeX
@article{Zhang_2025, title={Scalable and Efficient Probabilistic Inference for Bayesian Deep Learning and Generative Modeling}, volume={39}, url={https://ojs.aaai.org/index.php/AAAI/article/view/35129}, DOI={10.1609/aaai.v39i27.35129}, abstractNote={Probabilistic inference is a fundamental challenge in machine learning, spanning tasks from approximate Bayesian inference to generative AI. In this talk, I will present theoretically-guaranteed scalable and efficient probabilistic inference with applications in Bayesian deep learning and generative modeling. First, I will introduce a new compute paradigm for probabilistic inference that leverages modern accelerators, specifically low-precision and sparsity, to significantly speed up inference while preserving accuracy. Next, I will present a new framework for efficient inference in discrete domains, utilizing gradient information—a largely overlooked feature of discrete distributions—to enable more informed and directional exploration. Finally, I will showcase experimental results demonstrating the effectiveness of these methods across various ML tasks, including Bayesian neural networks, energy-based models, and large language models.}, number={27}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Zhang, Ruqi}, year={2025}, month={Apr.}, pages={28737-28737} }