可扩展贝叶斯学习与posteriors
Scalable Bayesian Learning with posteriors
AI总结：
针对现代机器学习模型贝叶斯学习的计算挑战，本文引入可扩展PyTorch库posteriors，提出回火随机梯度马尔可夫链蒙特卡罗框架并改进深度集成以实现渐近无偏，通过实验验证其在冷后验效应研究和大语言模型应用中的效用。
摘要：
尽管在理论上具有吸引力，但现代机器学习模型的贝叶斯学习在计算上具有挑战性，因为它需要近似高维后验分布。在这项工作中，我们（i）引入posteriors，一个易于扩展的PyTorch库，提供通用实现，使贝叶斯学习可访问且可扩展到大数据和参数范围；（ii）提出随机梯度马尔可夫链蒙特卡罗的回火框架（在posteriors中实现），该框架无缝过渡到优化，并揭示对深度集成的微小修改，以确保它们对贝叶斯后验渐近无偏；（iii）通过实验展示并比较贝叶斯近似的效用，包括对冷后验效应的研究和大型语言模型的应用。
英文摘要：
Although theoretically compelling, Bayesian learning with modern machine learning models is computationally challenging since it requires approximating a high dimensional posterior distribution. In this work, we (i) introduce posteriors, an easily extensible PyTorch library hosting general-purpose implementations making Bayesian learning accessible and scalable to large data and parameter regimes; (ii) present a tempered framing of stochastic gradient Markov chain Monte Carlo, as implemented in posteriors, that transitions seamlessly into optimization and unveils a minor modification to deep ensembles to ensure they are asymptotically unbiased for the Bayesian posterior, and (iii) demonstrate and compare the utility of Bayesian approximations through experiments including an investigation into the cold posterior effect and applications with large language models.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
