Michael Mahoney
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 5 in the filters
on a stage with
who talks about the same things
nobody close enough yet
| title | conference | date |
|---|---|---|
| Why Deep Learning Works: Implicit Self-Regularization in Deep Neural Networks | Randomized Numerical Linear Algebra and Applications 2018 | 2018-09-24 |
Claim: deep nets develop implicit self-regularization visible in the singular-value spectra of layer weight matrices. Empirical toolset uses heavy-tailed… | ||
| Sampling for Linear Algebra, Statistics, and Optimization I | Foundations of Data Science Boot Camp 2018 | 2018-08-27 |
Randomized linear‑algebra sketches replace large matrices by sampled rows/columns or random projections (Hadamard, Gaussian, CountSketch) so downstream… | ||
| Sampling for Linear Algebra, Statistics, and Optimization II | Foundations of Data Science Boot Camp 2018 | 2018-08-27 |
Mixing importance sampling with a small uniform fraction reduces estimator variance, with an empirical sweet spot near half leverage plus half uniform (roughly… | ||
| Implementing Randomized Matrix Algorithms in Parallel and Distributed Environments | Parallel and Distributed Algorithms for Inference and Optimization (Simons Institute, Oct. 21–24, 2013) | 2013-10-21 |
Randomized matrix methods run in parallel and distributed settings by random-projection preconditioning and importance sampling, producing practical solvers. A… | ||
| Input-sparsity Time Algorithms for Embeddings and Regression Problems | Workshop on Succinct Data Representations and Applications (Simons Institute Big Data 2013) | 2013-09-16 |
Claims that L2 and L1 subspace embeddings can be built in near input-sparsity time by using a projection Pi = S D where D is a random diagonal (±1 for L2… | ||
| Past, Present and Future of Randomized Numerical Linear Algebra I | Big Data Boot Camp 2013 | 2013-09-03 |
Randomized sketches replace heavy SVDs by sampling columns/rows or by applying subsampled Hadamard or sign matrices, then uniform sampling; matrix… | ||
| Past, Present and Future of Randomized Numerical Linear Algebra II | Big Data Boot Camp 2013 | 2013-09-03 |
Claims concrete speed and accuracy tradeoffs for randomized matrix methods and shows what actually gets built and tested: use statistical leverage scores to… | ||
| nothing matches | ||