Hacker Newsnew | past | comments | ask | show | jobs | submit | wei_jok's commentslogin

If it works so well for the (who knows how many) people using the defaults, who is to say that they are “wrong”?


I think he makes a pretty good case for why they're wrong in the article. He also specifically addresses that question:

> I don’t know if it’s true that a plurality of people doing logistic regressions are using L2 regularization and lambda = 1, but the point is that it doesn’t matter. Unregularized logistic regression is the most obvious interpretation of a bare bones logistic regression, so it should be the default

> Why is this a problem? Because one might expect that the most basic version of a function should broadly work for most cases. Except that’s not actually what happens for LogisticRegression. Scikit-learn requires you to either preprocess your data or specify options that let you work with data that has not been preprocessed in this specific way.

Most people running an unparameterized logistic regression would expect that regression to work just fine on un-normalized data. However, a regularized LR is not going to work at all unless your data has been normalized. This is deeply counter-intuitive and has probably tripped thousands of people up who have no idea it even happened.


Not sure why this is downvoted. I think it's great and we may see users deliberately do such things to get companies to ban them, which leads to bigger publicity and awareness at little expense.

In this case, the player sacrificed the prize money and some e-status, but for the publicity it got, it was probably worth it.


Previous discussion (for some reason, it was removed off the front page pretty quickly, hmm): https://news.ycombinator.com/item?id=21189491


Just read through the comments here and it's obvious why it got flagged off the front page. Grade A flamewar material.


I see, thanks for the explanation.

Maybe I should've rephrased the title of the post better to prevent it next time.


I saw a "dupe" tag on it.


If you cannot watch the episode in your country, here is a link to the "Band in China" on facebook (subbed in traditional Chinese): https://www.facebook.com/fighterstudiohk/videos/396572967928...


Uhm? Facebook is the first thing that non-Western countries will block for political reasons.


magnet:?xt=urn:btih:645FEB655D770627403E61BD6DF817C8EE30492B&dn=South+Park+S23E02+HDTV+x264+SVA&tr=udp%3A%2F%2Ftracker.coppersurfer.tk%3A6969%2Fannounce&tr=udp%3A%2F%2Ftracker.leechers-paradise.org%3A6969%2Fannounce&tr=udp%3A%2F%2Ftracker.opentrackr.org%3A1337%2Fannounce&tr=http%3A%2F%2Ftracker.trackerfix.com%3A80%2Fannounce


Why is this link downvoted? If it's due to your views on piracy, torrents shouldn't be any worse that the pirate Facebook stream.


Oh, not block for political reasons (some copyright issues apparently).

My friends in Hong Kong and Canada couldn't watch the official stream for some reason, and got some copyright page instead: https://southpark.cc.com/full-episodes/s23e02-band-in-china


In Canada, The Comedy Network has exclusive rights to South Park (and several other Comedy Channel properties).


While most users in China don't have access to Facebook, it is still pretty cheap/easy† for Chinese citizens to buy access to a VPN that allows them to use services by Western companies (e.g. Facebook, Google, Twitter)

†: https://www.saporedicina.com/english/vpn-how-to-access-faceb...


I'm pretty sure that's simplified Chinese, not traditional.


Thanks. (To the other commenters: give them a break, not everyone is a native English speaker. I don't think that comment was machine generated)


Fair: I was tired, cranky, and jumped to a conclusion I shouldn't have. I was wrong and I apologise.


If you cannot watch the episode (due to copyright issues with various countries), here is a link to the "Band in China" on facebook (note that it has been subbed in traditional Chinese): https://www.facebook.com/fighterstudiohk/videos/396572967928...


Thanks. I couldn't read the WSJ article (paywall) so submitted the reuters article here.


When I google the WSJ article URL, and click the link from the search results, I don't get a paywall.



The picture of him in confinement is horrifying.


This post does not represent what HKers involved in the movement want, which is autonomy (as per Basic Law), not independence.


You are right in regards to the current movement. In the 5 demands it says, "...implementation of universal suffrage for Legislative Council and Chief Executive elections"

Which could feasibly be done within the confines of the basic law. It is true many pro-democratic HKers don't want independence.

For some more context for those reading into it: https://en.wikipedia.org/wiki/Hong_Kong_independence vs https://en.wikipedia.org/wiki/2019_Hong_Kong_protests

But I should also be complete and let you know there is a fledgling and growing movement, the so-called "Republic of Cantonia", who believe all Guangdong should be break into its own nation. You can see the flag here: https://commons.wikimedia.org/wiki/Flags_of_active_autonomis...


I saw a previous article earlier, but WSJ is generally paywalled and I can't read it, while NYTimes is less so.

https://news.ycombinator.com/item?id=21176976


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: