Timeline for Approximation of Wasserstein distance between $p_\theta$ and $p_{\theta + d\theta}$
Current License: CC BY-SA 4.0
5 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Oct 19, 2018 at 10:10 | comment | added | dohmatob | As a token of gratitute, I should mention that the Otto et Villani reference you mentioned in your answer got me deep-diving into the subject of measure concentration, with a eye towards machine-learning applications. Here is my first produce arxiv.org/pdf/1810.04065.pdf | |
| Oct 9, 2018 at 0:19 | history | edited | Michael Hardy | CC BY-SA 4.0 |
added 8 characters in body
|
| Aug 12, 2018 at 1:15 | comment | added | dohmatob | Also, Amari's works (e.g fluid.ippt.gov.pl/bulletin/%2858-1%29183.pdf) also appear to be good reference on the 2nd question (the answer is mostly positive). | |
| Aug 10, 2018 at 6:31 | comment | added | dohmatob | Thanks for the response. The Otto et Villani paper is on point. It also contains a strange pearl (a consequence of Talagrand's inequality): concentration of Gaussian measure for the $t$-blowup $B_t$ of a Borel set $B$ in $\mathbb R^d$, namely $\gamma_d(B_t) \ge 1-\exp(-\frac{1}{2}(t-\sqrt{1\log(1/\gamma_d(B))})^2)$. | |
| Aug 10, 2018 at 0:20 | history | answered | Gabe K | CC BY-SA 4.0 |