Research map / Probabilistic and scientific modeling / Variational and generative sampling
Scalable and Efficient Probabilistic Inference for Bayesian Deep Learning and Generative Modeling
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
An AAAI 2025 invited talk abstract presenting scalable, efficient probabilistic inference methods for Bayesian deep learning and generative modeling, including a new compute paradigm leveraging modern accelerators.
Problem
Probabilistic inference is a fundamental challenge spanning approximate Bayesian inference and generative AI, where scalability and efficiency are limiting.
Approach
Proposes a new compute paradigm for probabilistic inference that leverages modern accelerators, with theoretical guarantees for scalability and efficiency. Full details are not available beyond the abstract.
Limitations
- Full text unavailable; only abstract content is known.
Closest papers by meaning
- Scalable Bayesian Learning with posteriors (ICLR 2025 · similarity 0.87)
- OptScale: Probabilistic Optimality for Inference-time Scaling (AAAI 2026 · similarity 0.86)
- On the Hardness of Approximating Distributions with Tractable Probabilistic Models (NeurIPS 2025 · similarity 0.86)
- Improving Generalization with Flat Hilbert Bayesian Inference (ICML 2025 · similarity 0.86)
- VIKING: Deep variational inference with stochastic projections (NeurIPS 2025 · similarity 0.86)
- Scalable Power Sampling: Unlocking Efficient, Training-Free Reasoning for LLMs via Distribution Sharpening (ICML 2026 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.