تقرير
Towards Information Theory-Based Discovery of Equivariances
العنوان: | Towards Information Theory-Based Discovery of Equivariances |
---|---|
المؤلفون: | Charvin, Hippolyte, Volpi, Nicola Catenacci, Polani, Daniel |
سنة النشر: | 2023 |
المجموعة: | Computer Science Mathematics |
مصطلحات موضوعية: | Computer Science - Information Theory, Computer Science - Neural and Evolutionary Computing, Mathematics - Group Theory |
الوصف: | The presence of symmetries imposes a stringent set of constraints on a system. This constrained structure allows intelligent agents interacting with such a system to drastically improve the efficiency of learning and generalization, through the internalisation of the system's symmetries into their information-processing. In parallel, principled models of complexity-constrained learning and behaviour make increasing use of information-theoretic methods. Here, we wish to marry these two perspectives and understand whether and in which form the information-theoretic lens can "see" the effect of symmetries of a system. For this purpose, we propose a novel variant of the Information Bottleneck principle, which has served as a productive basis for many principled studies of learning and information-constrained adaptive behaviour. We show (in the discrete case and under a specific technical assumption) that our approach formalises a certain duality between symmetry and information parsimony: namely, channel equivariances can be characterised by the optimal mutual information-preserving joint compression of the channel's input and output. This information-theoretic treatment furthermore suggests a principled notion of "soft" equivariance, whose "coarseness" is measured by the amount of input-output mutual information preserved by the corresponding optimal compression. This new notion offers a bridge between the field of bounded rationality and the study of symmetries in neural representations. The framework may also allow (exact and soft) equivariances to be automatically discovered. Comment: 23 pages, 0 figures |
نوع الوثيقة: | Working Paper |
URL الوصول: | http://arxiv.org/abs/2310.16555 |
رقم الأكسشن: | edsarx.2310.16555 |
قاعدة البيانات: | arXiv |
الوصف غير متاح. |