Your data is low-rank, so stop wasting compute! In our new paper on low-rank thinning, we share one weird trick to speed up Transformer inference, SGD training, and hypothesis testing at scale. Come by ICML poster W-1012 Tuesday at 4:30!

Lester Mackey@lestermackey.bsky.social · 2y ago

New guarantees for approximating attention, accelerating SGD, and testing sample quality in near-linear time

So you want to skip our thinning proofs—but you’d still like our out-of-the-box attention speedups? I’ll be presenting the Thinformer at two ICML workshop posters tomorrow! Catch me at Es-FoMo (1-2:30, East hall A) and at LCFM (10:45-11:30 & 3:30-4:30, West 202-204)

Annabelle Michael Carrell@ab-carrell.bsky.social · last yr.

Your data is low-rank, so stop wasting compute! In our new paper on low-rank thinning, we share one weird trick to speed up Transformer inference, SGD training, and hypothesis testing at scale. Come by ICML poster W-1012 Tuesday at 4:30!

new working paper! we (me, Su Lin Blodgett, @ninamarkl.bsky.social) examine how recent marketing of LLMs extends older discourses that cast workers as bundles of skills, and unpack the false promises of empowerment these discourses embed, in times of precarity tisjune.github.io/papers/aarhu...

Looking forward to this year's edition! With great speakers: Ryan McDonald Yulan He @vn-ml.bsky.social @antonisa.bsky.social Raquel Fernandez @annarogers.bsky.social Preslav Nakov @mohitbansal.bsky.social @eunsol.bsky.social Marie-Catherine de Marnefffe !

AthNLP - Athens Natural Language Processing Summer School@athnlp.bsky.social · last yr.

📢 10 Days Left to apply for the AthNLP - Athens Natural Language Processing Summer School! ✍ Get your applications in before June 15th! athnlp.github.io/2025/cfp.html

my lab (lacns.github.io) at @mpi-nl.bsky.social and @dondersinst.bsky.social is recruiting for two PhD and two postdoctoral positions funded by an @erc.europa.eu Consolidator - come join us! PhD: www.mpi.nl/career-educa... Postdoc: www.mpi.nl/career-educa... (please share widely)

Excited to share our ICLR 2025 oral "Residual Deep Gaussian Processes on Manifolds"! With @vabor112.bsky.social & @arkrause.bsky.social, we introduce manifold-to-manifold GPs that can be composed together, generalising deep GPs to manifolds. Applications include wind prediction & Bayes opt! 1/n

i can't believe how long we've spent fooling ourselves about the value of fully specified, massive matmuls instead of embracing the gods of sparsity

Recruiting a PhD candidate at U. of Amsterdam (funded, 4yr). We will use ML&NLP, prob. models, and user studies, to make adaptive scientific-assistant systems that communicate & justify decisions in ways helpful to experts. More: vene.ro/jobs.html Apply by May 18: werkenbij.uva.nl/en/vacancies...

Variational approximation with Gaussian mixtures is looking cute! So here it's just gradient descent on K(q||p) for optimising the mixtures means & covariances & weights... @lacerbi.bsky.social

antonio vergari ⚔️ short-circuiting@nolovedeeplearning.bsky.social · 2y ago

if they only used a mixture of those two Gaussians...

This review paper by @guillaume-garrigos.com on SGD-related algorithms is a fantastic resource, offering elegant, self-contained, and concise proofs in a single, accessible reference. arxiv.org/pdf/2301.11235

These phenomenon have been observed since early vision systems. It is important to report these things, though. Maybe it will permeate and we won’t keep making the same mistakes over and over

Janelle Shane@janelleshane.com · 2y ago

They trained an AI model on a widely used knee osteoarthritis dataset to see if it would be able to make nonsensical predictions - whether the patient ate refried beans, or drank beer. It did, in part by somehow figuring out where the x-ray was taken. www.dartmouth-health.org/about/news/a...

This is such a beautiful algorithm (and a nice analysis): to check if an array is sorted vs. far from being sorted (many entries need to be changed), just: - pick an element uniformly at random in the array - "forget" where it was - try to find it again via binary search Repeat this a few times.

Clément Canonne@ccanonne.github.io · 2y ago

<spoiler> The analysis is not obvious, but yes, that's the idea! * Repeat O(1) times: - Pick an index i uniformly at random, let x←A[i] - Do a binary search for x in A, end at index j - Return UNSORTED if i≠j * Return SORTED </spoiler>

I and hundreds other workers at the University of Amsterdam are on strike with @fnv.bsky.social www.linkedin.com/pulse/our-ha...

It is in our hands: To protect our safety and the right to protest, do more than re-formulating the house rules.

Column by anonymous FNV-member from UvA Protest is a fundamental right, and universities have a duty to facilitate and protect it. The violent events surrounding pro-Palestine protests this past year ...

linkedin.com

"AI can be bad but also it can be good" is just a really dumb way to talk about anything...it's the grade-school exercise of "make a list of pros and cons" but pressed into service for producing a sense of inevitability and making the medicine go down

OpenAI in 2024: “No AI for weapons or military” “Do use our AI to make weapons to hurt yourself or others” “Military is fine, but no AI for weapons” “Sure put it on battlefield drones” www.technologyreview.com/2024/12/04/1...

OpenAI’s new defense contract completes its military pivot

A new partnership with Anduril, announced today, will deploy AI on the battlefield. It represents an overhaul of the company’s position in just a year.

technologyreview.com

Blue skies 🦋 , hot (?) takes 🔥 Constrained output for LLMs, e.g., outlines library for vllm which forces models to output json/pydantic schemas, is cool! But, because output tokens cost much more latency than input tokens, if speed matters: bespoke, low-token output formats are often better.

I hope I am not late to the party (was away post-quals chilling) but here are some thoughts on why this is bad IMO: First, a disclaimer that I am writing this as an African who is a speaker of multiple African languages, NLP researcher of African languages, and HCI researcher focusing broadly on..

Dr Abeba Birhane@abeba.blacksky.app · 2y ago

this is a green flag for openai & meta to formally be arbitrators of our languages & mass exploit the population (& researcher that've poured their souls into low resource languages),all to throw unreliable AI that has so far proven to result in more harm than benefit www.reuters.com/technology/a...