Picture

Ioannis Mitliagkas (Γιάννης Μητλιάγκας) @bouzoukipunks

Associate prof. at the University of Montréal and Mila. Research scientist Google DeepMind. Previously Stanford; UT Austin. mitliagkas.github.io Montréal / Athens Joined June 2013
  • Tweets
    2K
  • Followers
    4K
  • Following
    877
  • Likes
    5K
Ioannis Mitliagkas (Γιάννης Μητλιάγκας) retweeted
RyanDOrazio Profile Picture

Ryan D'Orazio @RyanDOrazio

2 months ago

I’m also excited to be presenting this work (openreview.net/forum?id=4ZX2a…) 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!

Ioannis Mitliagkas (Γιάννης Μητλιάγκας) retweeted
RyanDOrazio Profile Picture

Ryan D'Orazio @RyanDOrazio

2 months ago

On my way to ICCOPT I decided to give PEPit (github.com/PerformanceEst…) 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

Ioannis Mitliagkas (Γιάννης Μητλιάγκας) retweeted
divyat09 Profile Picture

Divyat Mahajan @divyat09

2 months ago

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 Profile Picture

Divyat Mahajan @divyat09

4 months ago

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. https://t.co/lSNI54omxS

Ioannis Mitliagkas (Γιάννης Μητλιάγκας) retweeted
_Hiroki11x Profile Picture

Hiroki Naganuma @_Hiroki11x

2 months ago

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 Profile Picture

Accepted papers at TMLR @TmlrPub

2 months ago

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. https://t.co/5MSsrHFpb1

Ioannis Mitliagkas (Γιάννης Μητλιάγκας) retweeted
seblachap Profile Picture

Sébastien Lachapelle @seblachap

2 months ago

My thesis is now online! umontreal.scholaris.ca/items/f8670d1c… 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.

Ioannis Mitliagkas (Γιάννης Μητλιάγκας) retweeted
paulg Profile Picture

Paul Graham @paulg

4 months ago

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.

Ioannis Mitliagkas (Γιάννης Μητλιάγκας) retweeted
AntGois Profile Picture

António Góis @AntGois

5 months ago

Happy to announce "Performative Prediction on Games and Mechanism Design" was accepted at @aistats_conf 2025, and got spotlight at HAIC(@iclr_conf workshop) with @mhrnz_m @fernandopsantos @gauthier_gidel @SimonLacosteJ (Mila and UvA) arxiv.org/abs/2408.05146 Details below 1/9🧵

Ioannis Mitliagkas (Γιάννης Μητλιάγκας) retweeted
ReyhaneAskari Profile Picture

Reyhane Askari @ReyhaneAskari

4 months ago

Deliberate practice is accepted to #ICML2025 as a spotlight (top 2.6%!) 🚀

ReyhaneAskari Profile Picture

Reyhane Askari @ReyhaneAskari

6 months ago

Deliberate practice is accepted to #ICML2025 as a spotlight (top 2.6%!) 🚀

Ioannis Mitliagkas (Γιάννης Μητλιάγκας) retweeted
divyat09 Profile Picture

Divyat Mahajan @divyat09

4 months ago

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! 📜 arxiv.org/abs/2410.06303

Ioannis Mitliagkas (Γιάννης Μητλιάγκας) retweeted
hugo_larochelle Profile Picture

Hugo Larochelle @hugo_larochelle

4 months ago

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,…

Ioannis Mitliagkas (Γιάννης Μητλιάγκας) retweeted
alirezamh_ Profile Picture

Alireza Mousavi @alirezamh_

5 months ago

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]

Ioannis Mitliagkas (Γιάννης Μητλιάγκας) retweeted
SophieXhon11060 Profile Picture

Sophie Xhonneux @SophieXhon11060

4 months ago

If you are at @iclr_conf and are interested in making your RLHF really fast come find @mnoukhov and me at poster #582.

Ioannis Mitliagkas (Γιάννης Μητλιάγκας) retweeted
_Hiroki11x Profile Picture

Hiroki Naganuma @_Hiroki11x

5 months ago

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___ Profile Picture

Kotaro Yoshida @katoro13___

5 months ago

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

Ioannis Mitliagkas (Γιάννης Μητλιάγκας) retweeted
NicLoizou Profile Picture

Nicolas Loizou @NicLoizou

5 months ago

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 Profile Picture

Dimitris Oikonomou @dimitris_oik_gr

6 months ago

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 🧵👇

Ioannis Mitliagkas (Γιάννης Μητλιάγκας) retweeted
RyanDOrazio Profile Picture

Ryan D'Orazio @RyanDOrazio

5 months ago

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 Profile Picture

Ryan D'Orazio @RyanDOrazio

9 months ago

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

Ioannis Mitliagkas (Γιάννης Μητλιάγκας) retweeted
gkdziugaite Profile Picture

Gintare Karolina Dziugaite @gkdziugaite

5 months ago

Come chat with us @ ICLR on April 24th poster session to learn more about what matters in sparse LLM pretraining!

tjingrant Profile Picture

Tian Jin @tjingrant

5 months ago

Come chat with us @ ICLR on April 24th poster session to learn more about what matters in sparse LLM pretraining!

Ioannis Mitliagkas (Γιάννης Μητλιάγκας) retweeted
ReyhaneAskari Profile Picture

Reyhane Askari @ReyhaneAskari

5 months ago

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 Profile Picture

Reyhane Askari @ReyhaneAskari

6 months ago

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!

Ioannis Mitliagkas (Γιάννης Μητλιάγκας) retweeted
Riazi_Cafe_en Profile Picture

Math Cafe @Riazi_Cafe_en

5 months ago

Caltech's "Probability in High Dimensions" by Prof. Joel A. Tropp PDF: tropp.caltech.edu/notes/Tro21-Pr…

Ioannis Mitliagkas (Γιάννης Μητλιάγκας) retweeted
utkuevci Profile Picture

utku @utkuevci

5 months ago

I was a Fulbright Scholar from Turkey. It. has the goal of: "improving intercultural relations, cultural diplomacy, and intercultural competence between the people of the United States and other countries..." I guess no more. en.wikipedia.org/wiki/Fulbright…

zeynep Profile Picture

zeynep tufekci @zeynep

5 months ago

I was a Fulbright Scholar from Turkey. It. has the goal of: "improving intercultural relations, cultural diplomacy, and intercultural competence between the people of the United States and other countries..." I guess no more. en.wikipedia.org/wiki/Fulbright…

Ioannis Mitliagkas (Γιάννης Μητλιάγκας) retweeted
LesterMackey Profile Picture

Lester Mackey @LesterMackey

7 months ago

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

Trends for United States

Dodgers
47,6 B posts
$PACMAN
9.183 posts
Michigan
119 B posts
Yamamoto
19,8 B posts
UCLA
7.509 posts
Rand
24,4 B posts
Underwood
9.941 posts
Mississippi State
8.533 posts
UNLV
4.322 posts
Oklahoma
31,6 B posts
John Mateer
5.819 posts
#TacosVsSushi
3.969 posts
Orioles
28 B posts
#HailState
5.086 posts
Sherrone Moore
2.162 posts
Arizona State
5.933 posts
Stanford
10 B posts
Tanner Scott
3.021 posts
Aidan Chiles
1.662 posts
Jamo
2.337 posts

You might like

CSO & co-founder, Reliant AI. Ex RL research lead at Google Brain, DeepMind. Known for Atari 2600 RL benchmark, Distributional RL (MIT Press 2023).
Marc G. Bellemare
@marcgbellemare
16K Followers
Assoc Prof in ML @UniofOxford @StAnnesCollege @FLAIR_Ox/ RS @MetaAI, 2x dad. Ex: (A)PM @Google, DivStrat @GS, ex intern: @GoogleDeepmind, @GoogleBrain, @OpenAI
Jakob Foerster
@j_foerst
21K Followers
Harvard Professor. Full stack ML and AI. Co-director of the Kempner Institute for the Study of Artificial and Natural Intelligence.
Sham Kakade
@ShamKakade6
16K Followers
Machine learning professor at Mila / University of Montreal. Like to understand things - ML, optimization and statistics, but also philosophy, society and yoga.
Simon Lacoste-Julien
@SimonLacosteJ
3K Followers
machine learning and optimization @PrincetonCS & Google DeepMind Princeton, dad^3
Elad Hazan
@HazanPrinceton
14K Followers
ML theory nerd & AI non-enthusiast. thinking a lot about online learning these days! BTW you should go find me on another website where i post more actively
Gergely Neu
@neu_rips
11K Followers
Research Scientist @Google_Deepmind. PhD at @MILA.
Nan Rosemary Ke
@rosemary_ke
5K Followers
Thinking about thinking. Gemini ♊. Spent time at @Berkeley_EECS, @MPI_IS, @GoogleDeepMind.
Anirudh Goyal
@anirudhg9119
5K Followers
I am an assistant professor at Université de Montréal (UdeM) at DIRO, a core faculty member of Mila, and a Canada CIFAR AI chair holder
Gauthier Gidel
@gauthier_gidel
1K Followers
Research Scientist @MetaAI; PhD from @mcgillu + @Mila_Quebec; I organize ML Reproducibility Challenge (@repro_challenge). I do research in Multimodal ML
Koustuv Sinha
@koustuvsinha
3K Followers
Researcher in machine learning
Francis Bach
@BachFrancis
17K Followers
Csaba Szepesvari
@CsabaSzepesvari
11K Followers
Member of Technical Staff @RekaAILabs | Ex- @MetaAI (Core contributor of llama 3, tool use and reasoning)
Sharath Raparthy
@sharathraparthy
2K Followers
Incoming Assistant Professor @imperialcollege and @Mila_Quebec Affiliate member. Into Geometry ∩ Generative Models and AI4Science. Ex-@Mila_Quebec, @UofT.
Joey Bose
@bose_joey
3K Followers
Associate Professor @polymtl and @Mila_Quebec; Canada CIFAR AI Chair; Machine Learning Researcher. Pro-bono office hours: https://t.co/tK69DKRf9N?amp=1
Sarath Chandar
@apsarathchandar
6K Followers