The adaptive interpolation method: a simple scheme to prove replica formulas in Bayesian inference

• 成果类型: Article
• 署名作者: Barbier, Jean; Macris, Nicolas
• 署名单位: Swiss Federal Institutes of Technology Domain; Ecole Polytechnique Federale de Lausanne; Abdus Salam International Centre for Theoretical Physics (ICTP)
• 刊物名称: PROBABILITY THEORY AND RELATED FIELDS
• ISSN/ISSBN: 0178-8051
• DOI: 10.1007/s00440-018-0879-0
• 发表日期: 2019
• 页码: 1133-1185
• 关键词: tight bounds; sharp bounds; spin; MODEL

摘要

In recent years important progress has been achieved towards proving the validity of the replica predictions for the (asymptotic) mutual information (or free energy) in Bayesian inference problems. The proof techniques that have emerged appear to be quite general, despite they have been worked out on a case-by-case basis. Unfortunately, a common point between all these schemes is their relatively high level of technicality. We present a new proof scheme that is quite straightforward with respect to the previous ones. We call it the adaptive interpolation method because it can be seen as an extension of the interpolation method developped by Guerra and Toninelli in the context of spin glasses, with an interpolation path that is adaptive. In order to illustrate our method we show how to prove the replica formula for three non-trivial inference problems. The first one is symmetric rank-one matrix estimation (or factorisation), which is the simplest problem considered here and the one for which the method is presented in full details. Then we generalize to symmetric tensor estimation and random linear estimation. We believe that the present method has a much wider range of applicability and also sheds new insights on the reasons for the validity of replica formulas in Bayesian inference.