bouzoukipunks Profile Banner
Ioannis Mitliagkas (Γιάννης Μητλιάγκας) Profile
Ioannis Mitliagkas (Γιάννης Μητλιάγκας)

@bouzoukipunks

Followers
4K
Following
5K
Media
42
Statuses
2K

Associate prof. at the University of Montréal and Mila. Research scientist Google DeepMind. Previously Stanford; UT Austin.

Montréal / Athens
Joined June 2013
Don't wanna be here? Send us removal request.
@bouzoukipunks
Ioannis Mitliagkas (Γιάννης Μητλιάγκας)
3 years
Great things in '22, but I didn't tweet. 3-bullet summary: - Université de Montréal promoted me to associate professor with tenure! - Google Brain Montreal hired me as a part-time staff research scientist! - I got on mastodon: @bouzoukipunks@sigmoid.social 1/2
18
8
213
@divyat09
Divyat Mahajan
2 months
[1/9] While pretraining data might be hitting a wall, novel methods for modeling it are just getting started! We introduce future summary prediction (FSP), where the model predicts future sequence embeddings to reduce teacher forcing & shortcut learning. 📌Predict a learned
10
47
221
@HelennnnnnZhang
Helen Zhang
11 days
🚨 New paper! “Understanding Adam Requires Better Rotation-Dependent Assumptions.” Come check out our poster at @NeurIPSConf, or DM me if you would like to chat! 📅 Wednesday, December 3 🕐 4:30 PM PST 📍Exhibit Hall C,D,E #908
1
11
16
@RyanDOrazio
Ryan D'Orazio
5 months
I’m also excited to be presenting this work ( https://t.co/EHLDcLc2iC) at ICCOPT at USC. Theory aside there are some applications that may interest ppl in RL, games, and performative prediction. Let me know if you are in the area and want to chat!
openreview.net
Deep learning has proven to be effective in a wide variety of loss minimization problems. However, many applications of interest, like minimizing projected Bellman error and min-max optimization...
0
3
9
@RyanDOrazio
Ryan D'Orazio
5 months
On my way to ICCOPT I decided to give PEPit ( https://t.co/mUm5ldXclU) a try, and I wish I had used it sooner. In just a few hours I was able to confirm our theoretical results in our recent paper and I was able to get intuition that originally took me months without using it. 1/N
2
1
10
@divyat09
Divyat Mahajan
5 months
Presenting CRM at #ICML2025 📌 Wednesday, 16th July, 11 am 📍East Exhibition Hall A-B (E-2101) Lets chat about distribution shifts! Been deep into causality & invariance based perspectives, and recently exploring robust LLM pretraining architectures.
@divyat09
Divyat Mahajan
8 months
Happy to share that Compositional Risk Minimization has been accepted at #ICML2025 📌Extensive theoretical analysis along with a practical approach for extrapolating classifiers to novel compositions! 📜 https://t.co/J9JQLGyIWd
0
9
51
@_Hiroki11x
Hiroki Naganuma
6 months
I'm delighted to share that our paper has been accepted by #TMLR! We empirically observed signs of scaling laws regarding how the choice of pre-trained models affects OOD test errors and Expected Calibration Error on downstream tasks.
@TmlrPub
Accepted papers at TMLR
6 months
An Empirical Study of Pre-trained Model Selection for Out-of-Distribution Generalization and Cali... Hiroki Naganuma, Ryuichiro Hataya, Kotaro Yoshida, Ioannis Mitliagkas. Action editor: Mingsheng Long. https://t.co/3oaUwYOSos #accuracy #trained #deep
0
5
44
@seblachap
Sébastien Lachapelle
6 months
My thesis is now online! https://t.co/kdraSXMQLy This is more than just a list of publications. I invested a lot of time and passion writing this thesis in hope that it will make for an interesting read. Here's a summary of what you'll find in it.
7
17
117
@paulg
Paul Graham
7 months
It's strange to think it would be at all controversial to post this. But in a time of moral decay, the obvious becomes controversial.
281
1K
9K
@ReyhaneAskari
Reyhane Askari
8 months
Deliberate practice is accepted to #ICML2025 as a spotlight (top 2.6%!) 🚀
@ReyhaneAskari
Reyhane Askari
10 months
🚀 New Paper Alert! Can we generate informative synthetic data that truly helps a downstream learner? Introducing Deliberate Practice for Synthetic Data (DP)—a dynamic framework that focuses on where the model struggles most to generate useful synthetic training examples. 🔥
1
19
153
@divyat09
Divyat Mahajan
8 months
Happy to share that Compositional Risk Minimization has been accepted at #ICML2025 📌Extensive theoretical analysis along with a practical approach for extrapolating classifiers to novel compositions! 📜 https://t.co/J9JQLGyIWd
5
33
169
@hugo_larochelle
Hugo Larochelle
8 months
Today is my last day at Google. I started over 8 years ago, with a mandate to build a team doing bleeding edge AI research from Montreal, in what would be the first big tech AI research lab in the city. These years led to countless amazing scientific contributions from my team,
75
40
1K
@alirezamh_
Alireza Mousavi
8 months
I’m at ICLR presenting 2 posters. Check them out if you’re interested in deep learning theory, feature learning, and a theoretical approach to solving robustness! 📅 Thurs. 10am-12:30pm. Hall 3 + 2B, # 436“Robust Feature Learning for Multi-Index Models in High Dimensions” [1/2]
1
6
29
@SophieXhon11060
Sophie Xhonneux
8 months
If you are at @iclr_conf and are interested in making your RLHF really fast come find @mnoukhov and me at poster #582.
1
9
77
@_Hiroki11x
Hiroki Naganuma
8 months
Presenting our work, “Mastering Task Arithmetic: τJp as a Key Indicator for Weight Disentanglement,” this Friday, Apr 25, 3:00–5:30 p.m. Interested in task arithmetic? Please stop by our poster! #ICLR25 @Mila_Quebec
@katoro13___
Kotaro Yoshida
8 months
I’ll be attending #ICLR2025 to present our paper on the NTK-inspired regularization to improve task arithmetic and weight disentanglement 🇸🇬. 📍 Come check out our poster at Hall 3 + Hall 2B #497 ! 🔗 https://t.co/JoGzSWfDkm
1
7
30
@NicLoizou
Nicolas Loizou
8 months
Check out our recent work on understanding Sharpness-Aware Minimization (SAM). We address several key questions regarding the convergence properties of SAM in non-convex settings. To be presented at #ICLR2025 Joint work with @dimitris_oik_gr @HopkinsDSAI,@HopkinsEngineer 🧵👇
@dimitris_oik_gr
Dimitris Oikonomou
9 months
New #ICLR2025 paper: "Sharpness-Aware Minimization: General Analysis and Improved Rates"! Camera-ready: https://t.co/JC4XWHQO97 Code: https://t.co/bVLvvnVNBX Joint work with @NicLoizou
1
6
32
@RyanDOrazio
Ryan D'Orazio
8 months
This week I'll be at #ICLR25. If you like fundamental optimization results, I'll be presenting our work on surrogate losses for non-convex-concave min-max problems and learning value functions in deep RL (VIs more generally). Poster: #377 Thursday April 24 10am-12:30pm
@RyanDOrazio
Ryan D'Orazio
1 year
I'll be at #NeurIPS24 until Sunday. If you're interested in solving variational inequality problems with deep learning (e.g. min-max and projected Bellman error), come and checkout our poster on surrogate losses at the opt ml workshop.
0
6
28
@gkdziugaite
Gintare Karolina Dziugaite
8 months
Come chat with us @ ICLR on April 24th poster session to learn more about what matters in sparse LLM pretraining!
@tjingrant
Tian Jin
8 months
📣 The Journey Matters: Our #ICLR2025 paper shows how to pretrain sparse LLMs with half the size of dense LLMs while maintaining quality. We found that the average parameter count during sparse pre-training predicts quality, not final size. An MIT/Rice/Google/ISTA collab 🧵 1/N
0
9
44
@ReyhaneAskari
Reyhane Askari
8 months
Excited to be at #ICLR2025 next week! I'm currently on the job market for Research Scientist positions, especially in generative modeling, synthetic data, diffusion models, or responsible AI. Feel free to reach out if you have any openings!
@ReyhaneAskari
Reyhane Askari
10 months
🚀 New Paper Alert! Can we generate informative synthetic data that truly helps a downstream learner? Introducing Deliberate Practice for Synthetic Data (DP)—a dynamic framework that focuses on where the model struggles most to generate useful synthetic training examples. 🔥
0
11
67
@Riazi_Cafe_en
Math Cafe
8 months
Caltech's "Probability in High Dimensions" by Prof. Joel A. Tropp PDF: https://t.co/MYRP6EzlWB
0
36
265