Timeline for Uniform Convergence for Vectors
Current License: CC BY-SA 3.0
15 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Mar 8, 2019 at 17:39 | history | edited | YCor |
edited tags
|
|
| Nov 23, 2017 at 20:30 | comment | added | Aryeh Kontorovich | The answer below contains a hint. | |
| Nov 22, 2017 at 19:44 | answer | added | Aryeh Kontorovich | timeline score: 2 | |
| Nov 22, 2017 at 17:20 | comment | added | AvidLearner | @AryehKontorovich A hint will also be great :) | |
| Nov 22, 2017 at 17:15 | comment | added | Aryeh Kontorovich | Got it thanks. Unless I’m missing something this should be simple, will hopefully write an answer soon (unless someone beats me to it). | |
| Nov 22, 2017 at 17:10 | comment | added | AvidLearner | @AryehKontorovich The loss functions are not real-valued. $L_{\mathcal D}(f)$ is a vector, and so is $\hat L_{\mathcal S}(f)$ | |
| Nov 22, 2017 at 17:06 | comment | added | Aryeh Kontorovich | Why do you have the $\ell_1$ norm for the difference of the two losses? They're real numbers, so isn't it just an absolute value? | |
| Nov 22, 2017 at 16:57 | comment | added | AvidLearner | @AryehKontorovich to be zero vector, thanks again. | |
| Nov 22, 2017 at 16:57 | history | edited | AvidLearner | CC BY-SA 3.0 |
added 58 characters in body
|
| Nov 22, 2017 at 16:53 | comment | added | Aryeh Kontorovich | How do you define $g(0,0)$? | |
| Nov 22, 2017 at 16:30 | history | edited | AvidLearner | CC BY-SA 3.0 |
added 4 characters in body
|
| Nov 22, 2017 at 16:24 | comment | added | AvidLearner | Either would work, but I agree the latter makes more sense. I change it accordingly, thanks | |
| Nov 22, 2017 at 16:13 | history | edited | AvidLearner | CC BY-SA 3.0 |
clarified.
|
| Nov 22, 2017 at 16:11 | comment | added | Aryeh Kontorovich | I'm confused -- is the argument to $g$ a single vector or a pair of bits? | |
| Nov 22, 2017 at 16:02 | history | asked | AvidLearner | CC BY-SA 3.0 |