提出兼顾可靠性与效率的推理框架，实现可信不确定性估计的高效计算。
Foundations of Reliable Inference: Reliability-Efficiency Co-Design
- 从贝叶斯学习出发，构建统一框架提升推理可靠性。
- 在保持可信不确定性估计的前提下，显著降低计算开销。
- 适合关注模型可信度与实际部署效率的研究者。
可靠的推理要求人工智能模型不仅提供准确预测，还需给出可信赖的不确定性估计。近年来，贝叶斯学习的进步推动了该目标的实现，但随之而来的计算开销问题促使研究范式从单一追求可靠性转向可靠性和效率的协同设计——即在维持可信不确定性量化的同时减少计算负担。本论文从两个角度构建了一个统一框架，以回应核心问题：能否实现高效可靠的推理？结果表明，所提方法在多个基准数据集上实现了计算效率的显著提升，同时保持了高质量的不确定性估计，为实际部署中的可靠AI系统提供了理论与实践支持。
原文摘要 · Abstract (English)
Reliable inference requires that artificial intelligence (AI) models provide trustworthy uncertainty estimates, not merely accurate predictions. Recent advances in Bayesian learning have made significant progress toward this goal, and growing concerns about computational overhead have jointly shifted the design criterion from reliability alone to the co-design of reliability and efficiency, i.e., reducing computational overhead while preserving trustworthy uncertainty quantification. This thesis develops a unified framework from two perspectives to address the central question: can we efficiently perform reliable inference?
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。