MIT

dols

Dynamics Optimization and Learning Systems

12.S592

CURRENT: 12.S592  U/G      MIT REGISTRATION   Lec: F. 9-11  Rm: Zoom & 54-1827
Simultaneously offered at Instituto Politecnico National (IPN) Queretaro (via Zoom).

Instructor: Sai Ravela (ravela@mit.edu)

  • Offered since 2017, in earlier form since 2013
  • Dynamics, Optimization, and Information foundations of Machine Learning
  • ML-based System Dynamics and Optimization for Earth, Planets, Climate, and Life
  • Flexible participation model
  • Pre-reqs: Linear Algebra, Probability & Stat, a first course in ML, and some Systems preparation (at least one of) Statistical Signal Processing, Estimation, Control or Optimization

Seminar course 12.S592 is offered every term. Its syllabus follows four primary themes annually with an almost periodic, ahem, “50-shades of challenging grey matter” over approximately 50 weeks.  Some have stayed on in the course for six years!

Theme By Season

    • The Parsimony Principle for Model Building
      • Induction vs Reduction
      • Regularization vs Parsimony
    • Traditional
      • RKHS — spectral truncation
      • Model Selection Criteria.
    • Subset Selection
      • L0 , branch and bound, Mixed Integer Programming, Other approaches
    • Sparsity and L1
      • Various approaches including LASSO
      • Concentration Inequalities, Coherence, RIP and related concepts
    • Entropy and Informativeness
    • Co-Active Approaches to Model Parsimony