Misha Belkin
where else to find them
no profile links on file
what they talk about
where they keep going back
no series more than once — all 3 in the filters
on a stage with
never shared a talk
who talks about the same things
nobody close enough yet
| title | conference | date |
|---|---|---|
| The elusive generalization: classical bounds to double descent to grokking | Modern Paradigms in Generalization Boot Camp 2024 | 2024-08-27 |
Large neural models and a simple iterative kernel method produce the same surprising pattern: training loss is essentially zero while validation/test accuracy… | ||
| The Power and Limitations of Kernel Learning | Optimization, Statistics and Uncertainty | 2017-11-28 |
Argues that kernel machines reproduce many modern ML phenomena but suffer from nearly exponential eigenvalue decay that makes RKHS problems extremely… | ||
| Learning a Hidden Basis through Imperfect Measurements: Why and How | Information Theory, Learning and Big Data (Simons Institute, 2015) | 2015-03-16 |
Algorithm recovers an unknown orthonormal partial basis from evaluations and gradients of F(u)=sum_i g_i(u·e_i) by iterating gradient iteration (replace u by… | ||
| nothing matches | ||