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

Pearson correlation = cosine of the angle between centered random variables. Finite-variance centered random variables form a Hilbert space so it’s not a coincedence. Standard deviation is the length of the random variable as a vector in that space.

> Such a huge amount of ML can be framed through the lens of kernel methods

And none of them are a reinvention of kernel methods. There is such a huge gap between the Nadaraya and Watson idea and a working Attention model, calling it a reinvention is quite a reach.

One might as well say that neural networks trained with gradient descent are a reinvention of numerical methods for function approximation.


> One might as well say that neural networks trained with gradient descent are a reinvention of numerical methods for function approximation.

I don't know anyone who would disagree with that statement, and this is the standard framing I've encountered in nearly all neural network literature and courses. If you read any of the classic gradient based papers they fundamentally assume this position. Just take a quick read of "A Theoretical Framework for Back-Propagation (LeCun, 1988)" [0], here's a quote from the abstract:

> We present a mathematical framework for studying back-propagation based on the Lagrangian formalism. In this framework, inspired by optimal control theory, back-propagation is formulated as an optimization problem with nonlinear constraints.

There's no way you can read that a not recognize that you're reading a paper on numerical methods for function approximation.

The issue is that Vaswani, et al never mentions this relationship.

0. http://yann.lecun.com/exdb/publis/pdf/lecun-88.pdf


If you mention every mathematical relationship one can think of in your paper, it’s going to get rejected for being way over the page limit lol.

OLS estimator is the minimum-variance linear unbiased estimator even without the assumption of Gaussian distribution.

Yes, and if I remember correctly, you get the Gaussian because it's the minimum entropy (least additional assumptions about the shape) continuous distribution given a certain variance.

And given a mean.

It’s not open source, it’s “open core” SaaS.


It’s fine as an occasional stylistic choice, but using it repeatedly as a regular synonym for brown is a pragmatic and collocational error. The meaning is clear, but the wording is marked, and overuse makes the speech sound odd in everyday contexts.


coffee color won't be synonym for brown. it will be distinct color, just like strawberry, raspberry, straw, ruby, etc colors.


Using references is a standard industry practice for digital art and VFX. The main difference is that you are unable to accidentally copy a reference too close, while with AI it’s possible.


Why shouldn’t it boil down to “whataboutism”, aka comparison and putting things into context? Especially during UK’s obvious slide in to disguised authoritarianism.

One can also ask how HK ended up with English language and common law in the first place… though that wasn’t so recent.


It doesn't show that they "struggle". It shows that they don't behave according to modern standards. I wouldn't put much weight into an industry without sensible scientific base that used to classify homosexuality as a disease not so long ago. The external validity of the study is dubious, let's see comparison to no therapy, alternative therapy, standard therapy; and then compare success rates.


Surely Marx would disagree with such assessment and call it idealistic and not grounded in material reality?


There is no reason to buy into the whole Marxist framework just because you share one single sentiment that various thinkers had before and after him.


> one single sentiment

Lol alienation of labor is not a single "sentiment" - it's a core principle. So like it or not you share a core principle with Marx.


The sentiment is shared with Jean-Jacques Rousseau, Adam Smith, Wilhelm von Ketteler, Louis Blanc and probably lots of other less known people. Marx's theory of alienation is far more developed and nuanced than the generic cog-in-the-machine critique that is explored by many other people of various political inclination, not only Marx.


> sentiment

...

> theory

these two words aren't interchangeable

> Jean-Jacques Rousseau, Adam Smith, Wilhelm von Ketteler, Louis Blanc

...

> generic cog-in-the-machine critique that is explored by many other people

literally only one of the names you mentioned were writing post industrial revolution - the rest had literally no notion of "cog in the machine"

you're trying so hard to disprove basically an established fact: Marx's critique of exploitation of labor post industrial revolution is certainly original and significant in his own work and those that followed.


> these two words aren't interchangeable

Exactly. That's why you can't jump from "people don't feel like they own their labor" and "people bemoan their boss" to Marx's theory of alienation.

> literally only one of the names you mentioned were writing post industrial revolution - the rest had literally no notion of "cog in the machine"

But the very framing that this is an ill that is unique to industrial society is Marxist. Slavery, corveé labor, taxes, poor laborers, marginalisation existed for thousands years in one form or another.

> you're trying so hard to disprove basically an established fact: Marx's critique of exploitation of labor post industrial revolution is certainly original and significant in his own work and those that followed.

I don't dispute that Marx's critique of exploitation of labor post industrial revolution is original or significant. I dispute your claim that people who share similar sentiment have to agree with Marx's theory of alienation.


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

Search: