Mathematical Foundations of Machine Learning [electronic resource] /
Mathematical Foundations of Machine Learning [electronic resource] /
edited by Helmut Bölcskei.
- online resource.
Mathematical Foundations of Machine Learning (MFML) is a forum for the publication of papers concerned with all pure and applied mathematical aspects of machine learning, with a particular focus on foundational work. Areas of interest include, inter alia, functional analysis, approximation theory, harmonic analysis, partial differential equations, combinatorics, probability theory, statistics, geometry, algebra, analytic number theory, complex analysis, linear algebra, group theory, representation theory, theoretical computer science, complexity theory, numerical analysis, algebraic geometry, mathematical logic, geometric measure theory, and optimization theory. All papers must be characterized by originality and mathematical rigour. We explicitly encourage papers of conceptual value residing in the synthesis of mathematical theories and their application to fundamental problems in machine learning theory and practice. Survey papers are welcome as well and must exhibit originality in the synthesis of the material and their vantage point. .
3059-3492 = Math. Found. Mach. Learn.
44439 local
Mathematics.
Mathematics.
Machine learning.
Mathematics.
Mathematics and Computing.
Machine Learning.
Mathematical Foundations of Machine Learning (MFML) is a forum for the publication of papers concerned with all pure and applied mathematical aspects of machine learning, with a particular focus on foundational work. Areas of interest include, inter alia, functional analysis, approximation theory, harmonic analysis, partial differential equations, combinatorics, probability theory, statistics, geometry, algebra, analytic number theory, complex analysis, linear algebra, group theory, representation theory, theoretical computer science, complexity theory, numerical analysis, algebraic geometry, mathematical logic, geometric measure theory, and optimization theory. All papers must be characterized by originality and mathematical rigour. We explicitly encourage papers of conceptual value residing in the synthesis of mathematical theories and their application to fundamental problems in machine learning theory and practice. Survey papers are welcome as well and must exhibit originality in the synthesis of the material and their vantage point. .
3059-3492 = Math. Found. Mach. Learn.
44439 local
Mathematics.
Mathematics.
Machine learning.
Mathematics.
Mathematics and Computing.
Machine Learning.