HNHacker News
TopNewBestAskShowJobs

sbpayne

186 karma · joined April 24, 2015

skylarbpayne.com me@skylarbpayne.com
submissionscomments
sbpayne··on Mean Squared Terror – GridSearch Is Not Enough
I was mostly referring to this bit from the article: “Notice how the model that has the lowest mean squared error is also the model that causes the most bias between groups for higher skill levels. This increase in bias cannot be blamed merely on the data. It’s the choice of the model that increases this bias which is the responsibility of the algorithm designer.”

My reading of the plots is that the difference between the groups seems to grow beyond what is present in the data. Do you not think this is amplified?

As for conditioning on a biased variable; this post uses a contrived example for sure. But the same thing happens with variables that correlate with the “naughty” variable (perhaps author should have explicitly showed this to drive the point?)

Removing all variables that correlate with “naughty variables” is a pretty difficult task itself without having something to detect the correlation and tell you. At least that’s been my experience.

sbpayne··on Mean Squared Terror – GridSearch Is Not Enough
I find it interesting that you said: “Only an idiot would say the output of a model has anything to do with the moral question that of how things should be.”

My understanding of the article is that people often share this sentiment, but they often believe this property implies that an optimization procedure will only reflect bias rather than amplify it. Then the author goes on to show that this perceived implication is incorrect.

I.e. your algorithm not understanding an existing bias does not mean it won’t amplify bias — it means it won’t care, which is precisely what allows it to amplify the bias. Because the bias exists in the underlying data, your algorithm can discover and overfit to that bias. Without a “regularizer” to control for this, it’s probably a bad idea to think the algorithm does not amplify bias.

So if my understanding of your comment and the author’s post are right, I think you would both agree that at the end of the day: something needs to explicitly control for the moral question of how things should be, because the general optimization procedures we use do/will not. Is that a fair statement?

sbpayne··on Raft Is So Fetch: The Raft Consensus Algorithm Explained Through Mean Girls
I didn’t realize this is what I was looking for all my life
sbpayne··on Single Headed Attention RNN
Did anyone one else read "SHA-RNN" as "SHHHAAAAARRRROOOOONNN" in Ozzy's voice?
sbpayne··on Ask HN: Resources for engineers new to system design
Really want to put a +1 on this. I thought it was an excellent, practical treatment of many distributed systems concepts.
sbpayne··on Ask HN: What were/are you doing at age 25? What would you change?
I'm 25 now, so can't really answer the advice question. As for what I'm doing:

* Just ended a 5 year relationship that I felt was ultimately going to hold me back in life * Saying yes to more things that scare the hell out of me -- those things are often the most fun (a way to beat the anxiety out of me _shrug_) * Working as a machine learning tech lead at a large tech company and considering the possibility of going into management soonish * Working on being really intentional with my time and who I spend it with * Working on health in all aspects (physical, mental, emotional, and financial)

sbpayne··on MLflow: An Open Source Machine Learning Platform
The open source alternatives you list seem to only provide experimentation logging. ML Flow seems to support more (such as model deployment).

Not to claim that the deployment processes are _good_, just that MLFlow seems more general than these open source alternatives listed here.

sbpayne··on Ask HN: Organizing company knowledge?
I can second the recommendation of notion. It's worked very well for my organization / productivity needs.

However, I work at a large company that has adopted Confluence, so I'm stuck with that for organizational knowledge.

sbpayne··on C++ and the Culture of Complexity (2013)
YES. 100x yes to this. I started a new job some time ago where Java / Scala were mainly used (prior C++ background).

I can logically step through flow control and figure most things out. Except the amount of "magic" for the sake of reducing boiler plate made debugging some issues really tricky.

Anytime I'm about to reduce boiler plate somehow, I try to ask myself whether it's going to introduce some type of tribal knowledge. That is, will someone without any knowledge of e.g. this codegen be able to step through and understand what's going on.

I feel that people reduce boiler plate without constraints far too often

sbpayne··on A therapy chatbot and app for depression and anxiety
Woebot is not for talk therapy; it applies cognitive behavioral therapy. Since it's a skill based approach, I don't think it's crazy to think a chat bot could effectively approximate that type of therapy. It's much less open ended than talk therapy.

I don't think we'll see effective talk therapy chat bots for quite some time.

sbpayne··on David Eppstein's Wikipedia Gallery Contributions
I took courses with Eppstein at UCI. I was always impressed with his ability to construct clear example diagrams to explain any question.

Glad to see some of these great diagrams were shared with a wider audience :)

sbpayne··on Designing Data-Intensive Applications
I was very impressed with the quality and depth of the book. I also appreciated how unbiased it felt. I feel that so many books tout approach/technology X as the best approach, but Martin really did a great job at explaining trade offs of various approaches and possible solutions to the problems they introduce. Highly recommended--especially considering getting the Amazon price point (~ $25).
sbpayne··on Why I Don’t Talk to Google Recruiters
Sure. But at the scale of e.g. Google, Amazon, etc. how often do you think they are performing these lower level computations?

From my experience: very frequently.

So it's useful at these corporations for all engineers to have this understanding, I think.

sbpayne··on Turning the database inside-out with Apache Samza (2015)
What he proposes here seems to be:

Service -> Messaging Broker (Kafka) -> Consumers (Samza) -> View, where writes go to service and reads read from a view.

However, I more often see a CDC (change data capture) approach used in practice:

Service -> DB -> CDC -> Messaging Broker -> Consumers -> View

My understanding is that there were three reasons that this was the case:

1) Many already had some conventional DB in place, so it was easier to slap a CDC + Messaging Broker to get a lot of the benefits with less infra changes.

2) You require strong consistency

3) Messaging broker of choice might not be durable enough to entrust your writes to.

My understanding is that Kafka is durable (as this article states), so aside from (1) and (2) is there a strong reason to prefer a CDC approach?

sbpayne··on Welcome to the AI Conspiracy: The ‘Canadian Mafia’ (2015)
In before Shcmidhuber gets pissed he wasn't mentioned.

Edit: To be clear, I mean as one of the people who kept deep learning alive -- as a part of this "trio".

sbpayne··on Some Functional Programmers Are Arrogant
... Is this thread just filled with stereo types?
sbpayne··on How do machines learn meaning?
well the idea is that a word's meaning can be derived from its context (those context clues from grade school strike again). The co located words are simply the context. Since "ship" and "boat" frequently occur in similar contexts, they are similar words.

Honestly, this blog post felt like they were trying to explain word2vec for the hundredth time, but tried real hard to explain it differently--so much so that it just made it more confusing.

sbpayne··on Ask Me Anything: Dynamic Memory Networks for Natural Language Processing
I skimmed through, but I can't see any radically different from Facebook's Memory Networks. Anyone else see a big difference?
sbpayne··on Researcher who exploits bug in Starbucks gift cards gets rebuke, not love
My problem is this line: "As a professional penetration tester, Homakov knows better than most people that hackers should never access someone else's computer network or account without explicit permission."

He did neither of this. He used forms that Starbucks had in place (which they expect customers to use).

sbpayne··on What If Students Could Fire Their Professors?
Yeah, this is certainly ridiculous. Student ratings often correlate more with grades than they do actual effectiveness of professors.

The professors who inflate grades (and thus are really the ones that are diminishing educational value) are the ones who would keep their jobs.

I like the place this is coming from (there's zero accountability from students to professors). But such an extreme measure is something I feel would work against the end goal.

sbpayne··on Aetherial Symbols
I feel his explanation of activity vectors closely resembles/indicates Hebbian learning rules (due to the dependence on co-occurrences).

Pierre Balid from UCI has a paper coming soon about the theory behind learning rules; I think it might present some interesting ideas for this work from Hinton.

← PreviousPage 3 of 3