| 2025 | ACSSC | Pixel-Based Similarities as an Alternative to Neural Data for Improving Convolutional Neural Network Adversarial Robustness. | Elie Attias, Cengiz Pehlevan, Dina Obeid |
| 2025 | ACSSC | Spectral regularization for adversarially-robust representation learning. | Sheng Yang, Jacob A. Zavatone-Veth, Cengiz Pehlevan |
| 2025 | ICLR | The Optimization Landscape of SGD Across the Feature Learning Strength. | Alexander B. Atanasov, Alexandru Meterez, James B. Simon, Cengiz Pehlevan |
| 2025 | ICLR | How Feature Learning Can Improve Neural Scaling Laws. | Blake Bordelon, Alexander B. Atanasov, Cengiz Pehlevan |
| 2025 | ICLR | Scaling Laws for Precision. | Tanishq Kumar, Zachary Ankner, Benjamin Frederick Spector, Blake Bordelon, Niklas Muennighoff, Mansheej Paul, Cengiz Pehlevan, Christopher R, Aditi Raghunathan |
| 2025 | ICLR | Do Mice Grok? Glimpses of Hidden Progress in Sensory Cortex. | Tanishq Kumar, Blake Bordelon, Cengiz Pehlevan, Venkatesh N. Murthy, Samuel J. Gershman |
| 2025 | ICLR | MLPs Learn In-Context on Regression and Classification Tasks. | William Lingxiao Tong, Cengiz Pehlevan |
| 2025 | ICML | Risk and cross validation in ridge regression with correlated samples. | Alexander B. Atanasov, Jacob A. Zavatone-Veth, Cengiz Pehlevan |
| 2025 | ICML | Deep Linear Network Training Dynamics from Random Initialization: Data, Width, Depth, and Hyperparameter Transfer. | Blake Bordelon, Cengiz Pehlevan |
| 2025 | ICML | A Model of Place Field Reorganization During Reward Maximization. | M. Ganesh Kumar, Blake Bordelon, Jacob A. Zavatone-Veth, Cengiz Pehlevan |
| 2025 | ICML | Adaptive kernel predictors from feature-learning infinite limits of neural networks. | Clarissa Lauditi, Blake Bordelon, Cengiz Pehlevan |
| 2025 | ICML | No Free Lunch from Random Feature Ensembles: Scaling Laws and Near-Optimality Conditions. | Benjamin S. Ruben, William Lingxiao Tong, Hamza Tahir Chaudhry, Cengiz Pehlevan |
| 2024 | ICLR | Depthwise Hyperparameter Transfer in Residual Networks: Dynamics and Scaling Limit. | Blake Bordelon, Lorenzo Noci, Mufan Bill Li, Boris Hanin, Cengiz Pehlevan |
| 2024 | ICLR | Grokking as the transition from lazy to rich training dynamics. | Tanishq Kumar, Blake Bordelon, Samuel J. Gershman, Cengiz Pehlevan |
| 2024 | ICML | A Dynamical Model of Neural Scaling Laws. | Blake Bordelon, Alexander B. Atanasov, Cengiz Pehlevan |
| 2023 | ICLR | The Onset of Variance-Limited Behavior for Networks in the Lazy and Rich Regimes. | Alexander B. Atanasov, Blake Bordelon, Sabarish Sainathan, Cengiz Pehlevan |
| 2023 | ICLR | The Influence of Learning Rule on Representation Dynamics in Wide Neural Networks. | Blake Bordelon, Cengiz Pehlevan |
| 2023 | ICLR | Correlative Information Maximization Based Biologically Plausible Neural Networks for Correlated Source Separation. | Bariscan Bozkurt, Ates Isfendiyaroglu, Cengiz Pehlevan, Alper Tunga Erdogan |
| 2023 | ICLR | Interneurons accelerate learning dynamics in recurrent neural networks for statistical adaptation. | David Lipshutz, Cengiz Pehlevan, Dmitri B. Chklovskii |
| 2022 | ICLR | Neural Networks as Kernel Learners: The Silent Alignment Effect. | Alexander B. Atanasov, Blake Bordelon, Cengiz Pehlevan |
| 2022 | ICLR | Learning Curves for SGD on Structured Features. | Blake Bordelon, Cengiz Pehlevan |
| 2022 | ICLR | Capacity of Group-invariant Linear Readouts from Equivariant Representations: How Many Objects can be Linearly Classified Under All Possible Views? | Matthew Farrell, Blake Bordelon, Shubhendu Trivedi, Cengiz Pehlevan |
| 2021 | ACSSC | Depth induces scale-averaging in overparameterized linear Bayesian neural networks. | Jacob A. Zavatone-Veth, Cengiz Pehlevan |
| 2020 | ICASSP | Blind Bounded Source Separation Using Neural Networks with Local Learning Rules. | Alper T. Erdogan, Cengiz Pehlevan |
| 2020 | ICML | Spectrum Dependent Learning Curves in Kernel Regression and Wide Neural Networks. | Blake Bordelon, Abdulkadir Canatar, Cengiz Pehlevan |
| 2020 | ICML | Associative Memory in Iterated Overparameterized Sigmoid Autoencoders. | Yibo Jiang, Cengiz Pehlevan |
| 2019 | ACSSC | A Closer Look at Disentangling in β-VAE. | Harshvardhan Sikka, Weishun Zhong, Jun Yin, Cengiz Pehlevan |
| 2019 | ICASSP | A Spiking Neural Network with Local Learning Rules Derived from Nonnegative Similarity Matching. | Cengiz Pehlevan |
| 2018 | ACSSC | Biologically Plausible Online Principal Component Analysis Without Recurrent Neural Dynamics. | Victor Minden, Cengiz Pehlevan, Dmitri B. Chklovskii |
| 2017 | ACSSC | A clustering neural network model of insect olfaction. | Cengiz Pehlevan, Alexander Genkin, Dmitri B. Chklovskii |
| 2016 | ACSSC | Do retinal ganglion cells project natural scenes to their principal subspace and whiten them? | Reza Abbasi-Asl, Cengiz Pehlevan, Bin Yu, Dmitri B. Chklovskii |
| 2016 | ACSSC | Self-calibrating neural networks for dimensionality reduction. | Yuansi Chen, Cengiz Pehlevan, Dmitri B. Chklovskii |
| 2014 | ACSSC | A Hebbian/Anti-Hebbian network for online sparse dictionary learning derived from symmetric matrix factorization. | Tao Hu, Cengiz Pehlevan, Dmitri B. Chklovskii |
| 2014 | ACSSC | A Hebbian/Anti-Hebbian network derived from online non-negative matrix factorization can cluster and discover sparse features. | Cengiz Pehlevan, Dmitri B. Chklovskii |
| 2013 | ACSSC | A neuron as a signal processing device. | Tao Hu, Zaid J. Towfic, Cengiz Pehlevan, Alex V. Genkin, Dmitri B. Chklovskii |