Break reading
Spring break started yesterday, and I’ve been doing a little reading on topics that have reared their heads over this term: differential geometry, discrepancy, VC dimension, and pattern analysis. Or browsing rather, since to actually absorb this material at a serious level, I’d have to spend way more time on it than I’m willing to. I’m on break, after all.
I’m going to list all my sources here so I can continue this line of inquiry at my leisure in the future. Maybe others will find them interesting (the last three are available online):
- Introduction to Smooth Manifolds. Lee
- A Course in Differential Geometry. Aubin
- Optimization Algorithms on Matrix Manifolds. Absil, Mahony, Sepulchre
- The Discrepancy Method. Chazelle.
- Kernel Methods for Pattern Analysis. Shawe-Taylor, Cristianini
- A Tutorial on Support Vector Machines for Pattern Recognition. (paper) Burges
- Introduction to Statistical Learning Theory. (paper) Bousquet, Boucheron, Lugosi
- Concentration-of-measure Inequalities. (lecture notes) Lugosi
I’m also looking for a good reference (preferably a survey paper) on spectral partitioning, the Fiedler vector, and all that magical stuff. I’ve found some stuff that mentions them, or uses the results, but no proofs.