#  Resources 

 



## LECTURE NOTES, REVIEWS AND BLOG POSTS

[Replica Method for the Machine Learning Theorist - Part 1](https://windowsontheory.org/2021/08/11/replica-method-for-the-machine-learning-theorist-part-1-of-2/), by Blake Bordelon, Haozhe Shan, Abdul Canatar, Boaz Barak, Cengiz Pehlevan  
  
[Replica Method for the Machine Learning Theorist - Part 2](https://windowsontheory.org/2021/08/11/replica-method-for-the-machine-learning-theorist-part-2-of-2/), by Blake Bordelon, Haozhe Shan, Abdul Canatar, Boaz Barak, Cengiz Pehlevan  
  
[Lecture notes on the replica method for Wishart matrix eigenvalues](https://jzv.io/assets/pdf/wishart_eigenvalue_and_gaussian_data_pca_replica_notes.pdf), by Jacob Zavatone-Veth  
  
[A brief introduction to the neural network Gaussian process from the perspective of mean field theory](https://jzv.io/assets/pdf/lecture_notes_on_nngp_from_mft.pdf), by Jacob Zavatone-Veth

[Lecture Notes on Infinite-Width Limits of Neural Networks](/file_url/276), Cengiz Pehlevan and Blake Bordelon, prepared for 2023 Princeton ML Theory Summer School

[Infinite Limits of Neural Networks](https://kempnerinstitute.harvard.edu/research/deeper-learning/infinite-limits-of-neural-networks/), Deeper Learning Blog, by Alex Atanasov, Blake Bordelon and Cengiz Pehlevan

[A Dynamical Model of Neural Scaling Laws](https://kempnerinstitute.harvard.edu/research/deeper-learning/a-dynamical-model-of-neural-scaling-laws/), Deeper Learning Blog, by Blake Bordelon, Alex Atanasov and Cengiz Pehlevan

[Scaling and renormalization in high-dimensional regression](https://arxiv.org/abs/2405.00592), by Alex Atanasov, Jacob Zavatone-Veth, Cengiz Pehlevan

[Disordered Dynamics in High Dimensions: Connections to Random Matrices and Machine Learning](https://arxiv.org/abs/2601.01010), by Blake Bordelon and Cengiz Pehlevan

[Solvable Model of In-Context Learning Using Linear Attention](https://kempnerinstitute.harvard.edu/research/deeper-learning/solvable-model-of-in-context-learning-using-linear-attention/), Deeper Learning Blog, by Mary Letey

[Anytime Pretraining: Horizon-Free Learning-Rate Schedules with Weight Averaging](https://kempnerinstitute.harvard.edu/research/deeper-learning/anytime-pretraining-horizon-free-learning-rate-schedules-with-weight-averaging/), Deeper Learning Blog, by Alexandru Meterez\*, Pranav Ajit Nair\*, Depen Morwani\*, Cengiz Pehlevan, Sham Kakade

[Jailbreak Scaling Laws for Large Language Models: Polynomial–Exponential Crossover](https://kempnerinstitute.harvard.edu/research/deeper-learning/jailbreak-scaling-laws-for-large-language-models-polynomial-exponential-crossover/), Deeper Learning Blog, by Indranil Halder, Annesya Banerjee, Cengiz Pehlevan

## CODE

[Group GitHub](https://github.com/Pehlevan-Group)

## VIDEOS

[Physics of Learning Collaboration Webinar Series](https://www.physicsoflearning.org/webinar-series)

[KITP Program on Deep Learning from the Perspective of Physics and Neuroscience](https://online.kitp.ucsb.edu/online/deeplearning23/)  
  
[Pehlevan Group Youtube Channel](https://www.youtube.com/channel/UCwQOIlGUTKcl-uMeQENb5JQ)



 

   ![Logo](/sites/g/files/omnuum6471/files/styles/hwp_1_1__960x960_scale/public/pehlevan/files/dina_logo.jpg?itok=LCu1oZzk)