Abdulkadir Canatar

Research Fellow @FlatironCCN. Theoretical Neuroscience, Machine Learning, Physics. Prev: @Harvard and @sabanciu

[Chanwoo Chun @ChunChanWoo]

1/6
Excited to share our #ICLR2026 paper:

Estimating Dimensionality of Neural Representations from Finite Samples

with @canatar_a, @s_y_chung, and Daniel Lee.

Paper: https://t.co/t5gPakYSbF

[Physical Review E @PhysRevE]

A new statistical mechanics framework quantifies how the geometrical properties of neuronal representation affect continuous decoding of tasks and task performance — a key question in computational #neuroscience and with implications for #DeepLearning.

https://t.co/1urM8fFT4W

[Cengiz Pehlevan @CPehlevan]

Very excited to be a part of this amazing collaboration! Thanks @SimonsFdn for the support!

[Alex Atanasov @ABAtanasov]

If you’re an undergrad interested in shaping the future of AI, you can either fine-tune underwhelming language models at a leading AI lab OR you can join the group of one of the most talented scientists I know, pursuing some of the most promising research at the intersection of AI, Neuro, Scaling, and Statistical Physics

[Abdulkadir Canatar @canatar_a]

@blake__bordelon @UTAustin @OdenInstitute Huge congratulations Blake! Excited to see the wonderful things you will create! 🎉🎉

[SueYeon Chung @s_y_chung]

🧵0/7
🚨 Spotlight @ICML2025 🚨

Chi-Ning and Hang have been thinking deeply about how feature learning reshapes neural manifolds, and what that tells us about generalization and inductive bias in brains and machines.

They put together the thread below, which I’m sharing on their behalf 👇Enjoy!

[Fatih Dinc @fatihdin4en]

As we say in Turkish "Yasasin 23 Nisan!"

BTF is now officially accepting funding applications for summer research internships: https://t.co/nSyQ9JwuyT

The program requires you to apply with a mentor, who can be a PhD or a postdoc in a US institution. Good luck!

[Özgür Özel @eczozgurozel]

Tayyip Erdoğan’a helal olan millete haram olamaz!

Boykot demokratik haktır.

2008’de medya boykotu başlatan Erdoğan’ın ta kendisidir.

Bugün boykotu kötüleyen şuursuzlar baş kötünün müritleridir.

Tutarsızlıktan utanmayanlar, yalandan medet umanlar yine rezil oldunuz.

Hadi buyrun…

[Stat.ML Papers @StatMLPapers]

Estimating Neural Representation Alignment from Limited Inputs and Features https://t.co/5pp2EbiWEx

[Kempner Institute at Harvard University @KempnerInst]

We are thrilled to share the appointment of @s_y_chung as an #KempnerInstitute Investigator, bringing her expertise in using #AI to understand #brain structure and function to @Harvard. Read the announcement: https://t.co/AzLAP2LCGN @hseas @harvardphysics

[SueYeon Chung @s_y_chung]

NYU-CDS article about MMCR (Maximum Manifold Capacity Representations): The key principle of MMCR is to maximize the number of image manifolds (generated by nuisance variations) that can be linearly decoded in the representations, hence maximizing the efficiency of the representation from the perspective of a decoder ('task-centric' efficient coding, or efficient 'decoding', but groups of responses defining a 'manifold' are variations of the same image, so it also has to do with efficiently representing stimuli).

The original idea of 'Manifold Capacity' comes from statistical mechanical analysis of the capacity of perceptrons, generalized from discrete points to 'neural manifolds'.

very nice to see the interaction between different fields: from a new theory (merging statistical physics, high-dim geometry and convex optimization) to a new SSL algorithm, a new brain model, and new theoretical analyses.

Check out the information-theoretic analysis of MMCR: https://t.co/8GAbtRD7Bw
Original MMCR paper: https://t.co/X60o2vPwqT
Original paper on Manifold Capacity: https://t.co/3CFTKxgae7

[Simons Institute for the Theory of Computing @SimonsInstitute]

We mourn the loss of our friend and founding benefactor, Jim Simons. Jim was visionary, brilliant, and generous beyond measure. He has left an indelible mark on our field.

[Simons Foundation @SimonsFdn]

It is with great sadness that the Simons Foundation announces the death of its co-founder and chair emeritus, James Harris Simons. Jim was an award-winning mathematician, a legendary investor and a generous philanthropist. https://t.co/w48DhauUVj

[Alex Atanasov @ABAtanasov]

[1/n] Thrilled that this project with @jzavatoneveth and @cpehlevan is finally out! Our group has spent a lot of time studying high dimensional regression and its connections to scaling laws. All our results follow easily from a single central theorem 🧵
https://t.co/A0Dh1iNT4q

[SueYeon Chung @s_y_chung]

🔥Lots of new theories on day 3 of Cosyne:

[3-100] capacity for nonlinear classification of manifolds

[3-105] theory of multitask learning (optimal repr geometry + geometric measures for data analysis)

[3-167] tuning diversity shapes efficient representation geometry

🧵👇🏻

[SueYeon Chung @s_y_chung]

👋Check out the latest findings from our lab at #COSYNE24 @CosyneMeeting

Thread & links to preprints to follow (1/n)🧵👇

[SueYeon Chung @s_y_chung]

Just arrived in New Orleans for #NeurIPS2023 this week.

Topics I am excited about: neuro-AI, neural manifolds (representation geometry), stat physics for machine learning, interpretability, relational & causal representations

My group is presenting their awesome work👇 (1/n)

[Jenelle Feather @jenellefeather]

At #NeurIPS2023? Interested in brains, neural networks, and geometry? Come by our **Spotlight Poster** Tuesday @ 5:15PM (#1914) on A Spectral Theory of Neural Prediction and Alignment.
w/ @canatar_a @s_y_chung @AlbertWakhloo

[Alex Williams @ItsNeuronal]

Short thread about our work at #NeurIPS2023. Topics include:

- representational similarity
- high-D covariance estimates
- noise correlations / stochastic representation
- optimal transport
- scientific applications of deep nets to audio data + social neuro

Details below👇

[Alex Atanasov @ABAtanasov]

Very happy to share this work in NeurIPS 2023 with @vyasnikhil96, @blake__bordelon, Sab Sainathan, @DepenKenpachi, and @CPehlevan on the consistent behavior of feature-learning networks across large widths https://t.co/XQB6EsAZGO. What is large width consistency? Read on! 1/n