Theodore Vasiloudis

Machine Learning scientist @amazon. Passed through @ververicaData, @pandoramusic, @spotify. Opinions and retweets my own.

[Theodore Vasiloudis @thvasilo]

After a long and winding road, our work on uncertainty estimation for online regression forests is now published in @JmlrOrg ! Big thanks to my co-authors @gdfm7 and Henrik for sticking through and getting this over the finish line! https://t.co/cb5PQfSI0f

[Andreas Damianou @adamianou]

Excited to be speaking at the Stanford Graph Learning workshop about GNNs for Spotify RecSys applications! The event is great with lots of interesting talks! Livestream here: https://t.co/C5eTHNAbvk

[Tianqi Chen @tqchenml]

A summer endeavor, developing MLC: the first open lecture series on ML compilation. Machine learning compilation is an emerging field for systematic optimization and deployment of AI workloads. Hope to share adventures and fun with the community https://t.co/SQ6nKvw0XL 🚀

[Theodore Vasiloudis @thvasilo]

@JmlrOrg the website seems to be down?

[Theodore Vasiloudis @thvasilo]

@stsffap @VervericaData @ApacheFlink Best of luck in your next steps Till, it was a great privilege to work with you!

[EFF @EFF]

In our latest episode of “How to Fix the Internet,” comedian and host of @WTFpod @marcmaron and @ProducerMcD tell never-before-shared details of the battle to save podcasting from a patent troll, in a case that EFF took all the way to the Supreme Court. https://t.co/aUFZ1zJa1j

[Amazon Science @AmazonScience]

ICYMI: The best science career advice we heard in 2021 from @alliekmiller, @DalianaLiu, @sneha_rajana, @crislopeslara, @thvasilo, and many others. Read the full article here: https://t.co/eMxk2YGma4

[Theodore Vasiloudis @thvasilo]

Me on my way to a conference

[Fabian Pedregosa @fpedregosa]

I'm starting a series of blog posts on "optimization nuggets": short and beautiful proofs in optimization (let me know what you think!). First one shows that SGD converges exponentially fast to a neighborhood of the solution:

https://t.co/WFVI5KSiS3

[Theodore Vasiloudis @thvasilo]

Well this is depressing 🥲 https://t.co/AzGv6DdCBi

[Theodore Vasiloudis @thvasilo]

This is a very well-written intro to the topic of automated reasoning, and glad to see the techniques making their way onto real products. Logic geeks will be happy to see this :)

[Amazon Science @AmazonScience]

To launch our new research area, @byroncook, head of the AWS Automated Reasoning group, wrote a "gentle introduction" to the field, with some simple code examples (including a two-line illustration of the halting problem). #reInvent #AutomatedReasoning https://t.co/VBX9ffFWDz

[Bryan Banks @BryanBanksPhD]

Whoever made this is my new favorite person.

[Theodore Vasiloudis @thvasilo]

Don't enjoy the doomscroll news on the right on the Twitter website? Current filter to get rid of them (you're already using uBlock Origin right?)

https://t.co/LYQnRvSJnm##div.r-1udh08x.r-1ifxtd0.r-rs99b7.r-1phboty.r-1867qdf.r-k0dy70.r-1ysxnx4.css-1dbjc4n:nth-of-type(3)

[Amazon Science @AmazonScience]

Join Amazon Scholars Michael I. Jordan, @mkearnsupenn, and Amazon VP and distinguished scientist Bernhard Schölkopf, as they discuss the history of machine learning in the past decade, its social impacts, the role of causal reasoning, and more. Register: https://t.co/Fp9KFBRmrI

[Adi Polak @AdiPolak]

"It works on My Machine" - MLOps edition:

[Theodore Vasiloudis @thvasilo]

@hspter Well the good news is that with the new infra bill, DOT will need to investigate their implications on safety (see Better headlights, less-threatening trucks section): https://t.co/amySjlKb8f

[Yuan (Terry) Tang @TerryTangYuan]

Excited to announce that we've finally released @XGBoostProject v1.0.0! This cannot happen without contributions from over 390 contributors and the support from the community. Thank you! #MachineLearning

Release notes: https://t.co/JMbbaIwArr
GitHub repo: https://t.co/Z0ukD2gsum

[Papers with Code @paperswithcode]

Graph neural networks are driving lots of progress in machine learning by extending deep learning approaches to complex graph data and applications.

Let’s take a look at a few methods ↓

[Omer Levy @omerlevy_]

What if I told you that fine-tuning T5-Large (0.8B params) on a couple hundred examples could outperform GPT-3 (175B params) on a bunch of tasks?

[Tim Dettmers @Tim_Dettmers]

I am excited to share my latest work: 8-bit optimizers – a replacement for regular optimizers. Faster 🚀, 75% less memory 🪶, same performance📈, no hyperparam tuning needed 🔢. 🧵/n

Paper: https://t.co/V5tjOmaWvD
Library: https://t.co/JAvUk9hrmM
Video: https://t.co/TWCNpCtCap