Picture

Annabelle Michael Carrell @annabelle_cs

Cambridge machine learning PhD student. Formerly Amazon, @JohnsHopkins. 🏳️‍🌈 she/her Baltimore, MD Joined December 2017
  • Tweets
    641
  • Followers
    589
  • Following
    645
  • Likes
    1K
annabelle_cs Profile Picture

Annabelle Michael Carrell @annabelle_cs

2 months ago

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 in 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_cs Profile Picture

Annabelle Michael Carrell @annabelle_cs

2 months ago

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 in 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 retweeted
OjewaleV Profile Picture

Ojewale Victor @OjewaleV

2 years ago

GRAD SCHOOL APPLICATION(2.0) 🧵 Got multiple fully funded PhD offers recently and realized from conversations I have been having that many people don't approach the application process intentionally. Sharing my application process doc as an example below. Open and Retweet 🔃

Annabelle Michael Carrell retweeted
XinyiChen2 Profile Picture

Xinyi Chen @XinyiChen2

3 years ago

Optimizer tuning can be manual and resource-intensive. Can we learn the best optimizer automatically with guarantees? With @HazanPrinceton, we give new provable methods for learning optimizers using a control approach. Excited about this result! buff.ly/3IoMOkN (1/n)

Annabelle Michael Carrell retweeted
AshokCutkosky Profile Picture

Ashok Cutkosky @AshokCutkosky

3 years ago

Neural networks are non-convex, and non-smooth. Unfortunately, most theoretical analysis is either convex, or smooth. Should we abandon the past? No! With @bremen79 and @n0royalroad, we import prior know-how via an *online to non-convex* conversion: arxiv.org/abs/2302.03775.

Annabelle Michael Carrell retweeted
PreetumNakkiran Profile Picture

Preetum Nakkiran @PreetumNakkiran

3 years ago

My favorite non-ML paper I read this year is probably "Bayesian Persuasion" (2011), which I somehow only found out about recently. Simple & beautiful. The first 2 pages are sufficient to be persuaded. web.stanford.edu/~gentzkow/rese…

Annabelle Michael Carrell retweeted
Michael_J_Black Profile Picture

Michael Black @Michael_J_Black

3 years ago

In the LLM-science discussion, I see a common misconception that science is a thing you do and that writing about it is separate and can be automated. I’ve written over 300 scientific papers and can assure you that science writing can’t be separated from science doing. Why? 1/18

Annabelle Michael Carrell retweeted
SuryaGanguli Profile Picture

Surya Ganguli @SuryaGanguli

3 years ago

1/Is scale all you need for AGI?(unlikely).But our new paper "Beyond neural scaling laws:beating power law scaling via data pruning" shows how to achieve much superior exponential decay of error with dataset size rather than slow power law neural scaling arxiv.org/abs/2206.14486

Annabelle Michael Carrell retweeted
sp_monte_carlo Profile Picture

Sam Power @sp_monte_carlo

3 years ago

cool uploads: arxiv.org/abs/2210.13574 'Understanding Linchpin Variables in Markov Chain Monte Carlo' - Dootika Vats, Felipe Acosta, Mark L. Huber, Galin L. Jones

Annabelle Michael Carrell retweeted
AnimaAnandkumar Profile Picture

Prof. Anima Anandkumar @AnimaAnandkumar

3 years ago

We prove open problem that Thompson sampling has optimal regret for linear quadratic control in any dimension. Previously only proven in one dimension. We develop novel lower bound on probability that TS gives an optimistic sample. @SahinLale @tkargin_ @Azizzadenesheli @Caltech

Arxiv_Daily Profile Picture

arXiv Daily @Arxiv_Daily

3 years ago

We prove open problem that Thompson sampling has optimal regret for linear quadratic control in any dimension. Previously only proven in one dimension. We develop novel lower bound on probability that TS gives an optimistic sample. @SahinLale @tkargin_ @Azizzadenesheli @Caltech

Annabelle Michael Carrell retweeted
konstmish Profile Picture

Konstantin Mishchenko @konstmish

3 years ago

Five years ago, I started my first optimization project, which was about asynchronous gradient descent. Today, I'm happy to present our new work (with @BachFrancis, M. Even and B. Woodworth) where we finally prove: Delays do not matter. arxiv.org/abs/2206.07638 🧵1/5

Annabelle Michael Carrell retweeted
PetarV_93 Profile Picture

Petar Veličković @PetarV_93

3 years ago

Proud to share our CLRS benchmark: probing GNNs to execute 30 diverse algorithms! ⚡️ github.com/deepmind/clrs arxiv.org/abs/2205.15659 (@icmlconf'22) Find out all about our 2-year effort below! 🧵 w/ Adrià @davidmbudden @rpascanu @AndreaBanino Misha @RaiaHadsell @BlundellCharles

Annabelle Michael Carrell retweeted
aminkarbasi Profile Picture

Amin Karbasi @aminkarbasi

3 years ago

Gradient Descent provably generalizes. I should say that our thinking was shaped and influenced by the amazing work done by the one and only @DimitrisPapail, the amazing couple @roydanroy and @gkdziugaite and of course @neu_rips, @mraginsky, @mrtz, @beenwrekt

DKalogerias Profile Picture

Dionysis Kalogerias @DKalogerias

3 years ago

Gradient Descent provably generalizes. I should say that our thinking was shaped and influenced by the amazing work done by the one and only @DimitrisPapail, the amazing couple @roydanroy and @gkdziugaite and of course @neu_rips, @mraginsky, @mrtz, @beenwrekt

Trends for United States

#SmackDown
23,6 B posts
Ryan Clark
8.128 posts
Chargers
38,3 B posts
Tylenol
28,1 B posts
Derek Carr
Department of War
88,6 B posts
#KCvsLAC
Louisville
3.757 posts
Eswatini
10,7 B posts
Alcaraz
61,5 B posts
#2KDay
78,6 B posts
#TSTheErasTour
1.565 posts
End of 1
16,1 B posts
#FreeAngel
1.297 posts
End 1Q
Parker Meadows
Schlittler
1.253 posts
Miller Moss
Kay Adams
Mike Johnson
24,3 B posts

You might like

Foundation Models for Generalizable Autonomy in Robotics. Assistant Professor in AI Robotics @GeorgiaTech. Prev @nvidia
Animesh Garg
@animesh_garg
29K Followers
Director, GenAI Research @Meta. Tech Lead of Movie Gen Meta. Past: MIT TR35, Llama3, Emu Video, ImageBind, DINO. Tweets and opinions are my own.
Ishan Misra
@imisra_
7K Followers
Machine Learning researcher at @Xaira_Thera (former @CambridgeEllis and @OxCSML). Opinions expressed are my own.
Emile Mathieu
@MathieuEmile
896 Followers
Secular Bayesian. Professor of Machine Learning @Cambridge_CL. Talent aficionado at https://t.co/RbJkoLguey Alum of @Twitter, Magic Pony and @Balderton
Ferenc Huszár
@fhuszar
42K Followers
machine learning, reinforcement learning, programming languages, handstands (he/him)
Tim Vieira
@xtimv
4K Followers
Assistant Professor of Computer Science at University of Maryland, College Park. NLP, CompLing, AI. she/her
Rachel Rudinger
@rachelrudinger
3K Followers
Research @OpenAI. Trained models for GPT5 Thinking / Mini; Contributor to gpt-oss, o3-mini, o1. Previously @SFResearch, PhD @Stanford.
Yu Bai
@yubai01
6K Followers
Assistant Prof. @CSatUSC | Researcher in #NLProc | Previously @uwnlp @allenai
Swabha Swayamdipta
@swabhz
7K Followers
NLP Researcher Stony Brook University Views my own.
Niranjan
@b_niranjan
2K Followers
🚨 I'm no longer active on Twitter. Find me on 🦋: @eringrant@bsky.social Senior Research Fellow @GatsbyUCL & @SWC_Neuro {learning, representations} in 🧠💭🤖
Erin Grant
@ermgrant
3K Followers
Asst. Prof. in CS at @BU_Tweets ≡ {Mechanistic, causal} {interpretability, NLP} ≡ Formerly: PhD @jhuclsp
Aaron Mueller
@amuuueller
2K Followers
Post-training @OpenAI. Previously: @GoogleDeepMind @UCLA @Tsinghua_Uni
Xiangning Chen
@XiangningChen
1K Followers
Assist. Prof at George Mason CS #nlproc MT, ASR, and documentation of endangered languages.
Antonis Anastasopoulo...
@anas_ant
3K Followers
Research Scientist at FAIR @AIatMeta & visiting researcher at Princeton @VisualAILab prev. PhD at New York University 🇺🇦
Polina Kirichenko
@polkirichenko
4K Followers
Research fellow at Flatiron Institute, working on understanding optimization in deep learning. Previously: PhD in machine learning at Carnegie Mellon.
Jeremy Cohen
@deepcohen
4K Followers