ICML and isotropic position of a convex body | I’m a bandit
[latexpage] ICML 2013 just finished a few days ago. The presentation that inspired me the most was the invited talk by Santosh Vempala. He talked about the relations between sampling, optimization,…
ICML 2013 just finished a few days ago. The presentation that inspired me the most was the invited talk by Santosh Vempala. He talked about the relations between sampling, optimization, integration, learning, and rounding. I strongly recommend Vempala’s short survey on these topics, it is an excellent read. I also would like to point out two papers by Vempala on optimization that are very interesting and exceptionally well written: the first paper (with Bertsimas) presents an optimal (in terms of oracle complexity) algorithm for convex optimization with a much better computational complexity…
saved by
related reading
- Geometry of random sections of isotropic convex bodiesarxiv.org
- survey.dvimath.uchicago.edu
- Distances between non-symmetric convex bodies: optimal bounds up to polylogarxiv.org
- SIAG on Optimization Views and News 33(1)siagoptimization.github.io
- [2608.00140] Discrepancy Theory: An Algorithmic and Geometric Perspectivearxiv.org
- An optimization perspective on log-concave sampling and beyond | Sinho Chewichewisinho.github.io
- rakhlin_mathstat_sp24.pdfmit.edu
- Six (and a half) intuitions for KL divergence — LessWronglesswrong.com
- Why Momentum Really Worksdistill.pub
- [2605.15522] Stochastic Non-Smooth Convex Optimization with Unbounded Gradientsarxiv.org
- Pen and Paper Exercises in Machine Learningarxiv.org
- John's ellipsoid theorem | Sidhanth Mohantysidhanthm.com