Main navigation | Main content

« fall 2019 - spring 2020 - summer 2020 »

This week | Next week | This semester | All future | Print view

This week | Next week | This semester | All future | Print view

Tuesday, March 12th 2019

4:00 pm:

Many diverse fields, such as applied mathematics, statistics, machine learning, data mining, econometrics, bioinformatics etc. are all concerned with estimation of data-analytic models. More recently, due to abundance of data and cheap computing power, machine learning (ML) algorithms have become very popular in various applications, even though many such algorithms are heuristics vaguely motivated by biological/ not mathematical/ arguments. This disconnect (between mathematics and practical applications) may seem strange, given the deep intrinsic connection between mathematics and natural sciences. Well-known historical examples include Kepler’s Laws and (classical) statistical science. The purpose of my talk is to explain various reasons for current disconnect, including (a) conceptual (philosophical) aspects; (b) technical (~mathematical) aspects and (c) non-technical (social) aspects. In particular, my talk will elaborate on different interpretation of philosophical concepts (of deductive and inductive reasoning), in classical statistics and in ML. This methodological difference will be further clarified via several basic assumptions underlying all ML methods – as presented in Vapnik-Chervonenkis (VC) learning theory. Further, I will discuss several ‘non-standard’ inductive problem settings (i.e., different from standard supervised learning) that often enable better generalization with finite training data.

The weekly calendar is also available via subscription to the physics-announce mailing list, and by RSS feed.