Peter Schulam

Scientist at Amazon Alexa AI. I’m interested in applied machine learning and building software systems. Views are my own.

[Will Townes @will_townes]

@WallaceUcsf Check out work by @david_sontag @ShalitUri in this area. Also @pschulam @suchisaria who use Gaussian processes instead of neural nets.

[Andrew Beam @AndrewLBeam]

@MaxALittle @filippie509 Gotta love that sweet sweet irony

[Peter Schulam @pschulam]

In fact, ML can be especially impactful in situations like this. The heuristics make excellent features for a linear model. The result is often good enough (or is a strong baseline). Keeping this in mind gives me a nice “playbook” for kicking off work on a new project.

[Peter Schulam @pschulam]

For some classification problems, a first analysis usually uncovers several heuristics that would work ~50-75% of the time. My gut reaction to this is often: “Do we really need to use machine learning here?” After all, I don’t want to be the fool with a hammer looking for nails.

[Sam Finlayson @IAmSamFin]

@pschulam How bout that Twitter algorithm

[Peter Schulam @pschulam]

@IAmSamFin 😂

[Peter Schulam @pschulam]

The majority of ML case studies floating around the internet are, unfortunately, fast food. I think this is a problem because we can’t share, learn from, and discuss our “recipes” as practitioners.

[Peter Schulam @pschulam]

I think this might follow from results reported by Jonathan Byrd and @zacharylipton in this great paper:

https://t.co/N756lEH7Jy

[Peter Schulam @pschulam]

There are lots of recent papers in the ML literature that look at how to detect when we can’t make reliable predictions. I often see this described as detecting “out of distribution” samples. This is unusual to me, though. The same value can come from two different distributions.

[Peter Schulam @pschulam]

When we talk about covariate shift, the support of the train and test distributions may be the same but the frequency of seeing a given input may have changed. This is important when we use low-capacity models, but maybe less so with the richer classes we use today.

[Peter Schulam @pschulam]

@IAmSamFin Great write-up on this (unfortunately?) evergreen debate; thanks for sharing! I liked your point about avoiding the “who owns regression” question. The same tool can be used to accomplish different things.

[Peter Schulam @pschulam]

Very interesting paper from @laurence_ai:

https://t.co/gMzzvw0Hdh

Not the intended message, I think, but brought one thing into focus for me:

[Peter Schulam @pschulam]

@TimRadtke Thanks for the link! This looks interesting; I’ll check it out.

[Peter Schulam @pschulam]

Stats journals often have a separate “applications” track. Does something like this exist for machine learning? I’m looking for good write ups of the nitty gritty details behind successful ML applications.

[Peter Schulam @pschulam]

This reminds me of what @lawrennd calls “decomposition” in his three D’s of ML system design.

https://t.co/i5SWem7xEN

[Peter Schulam @pschulam]

The thread below is the kind of thing that we need more of in “applied ML literature”. In this case, they didn’t really need a model, but I would love to read more about this kind of clever detective work.

[Matt Lerner @matthlerner]

After 17 years, we finally “cracked” a $100M churn problem at PayPal. Zero fancy tech. Just a spreadsheet, some simple SQL, and a physicist named Ben. 👇🏼

[Bayesian Health @bayesianhealth]

We've heard lots about #MachineLearning in healthcare, but usually with few specifics. A new paper in @AnnalsofIM, featuring our very own @suchisaria & @pschulam, cuts through the buzz and discusses the real applications and real benefits of clinical #AI: https://t.co/0HRNAVcEoR