Cengiz Pehlevan

Adaptive kernel predictors from feature-learning infinite limits of neural networks ICML 2025 A Model of Place Field Reorganization During Reward Maximization ICML 2025 Deep Linear Network Training Dynamics from Random Initialization: Data, Width, Depth, and Hyperparameter Transfer ICML 2025 Do Mice Grok? Glimpses of Hidden Progress in Sensory Cortex ICLR 2025 How Feature Learning Can Improve Neural Scaling Laws ICLR 2025 MLPs Learn In-Context on Regression and Classification Tasks ICLR 2025 No Free Lunch from Random Feature Ensembles: Scaling Laws and Near-Optimality Conditions ICML 2025 Risk and cross validation in ridge regression with correlated samples ICML 2025 Scaling Laws for Precision ICLR 2025 The Optimization Landscape of SGD Across the Feature Learning Strength ICLR 2025 A Dynamical Model of Neural Scaling Laws ICML 2024 Depthwise Hyperparameter Transfer in Residual Networks: Dynamics and Scaling Limit ICLR 2024 Grokking as the transition from lazy to rich training dynamics ICLR 2024 Infinite Limits of Multi-head Transformer Dynamics NeurIPS 2024 Partial observation can induce mechanistic mismatches in data-constrained models of neural dynamics NeurIPS 2024 Correlative Information Maximization: A Biologically Plausible Approach to Supervised Deep Neural Networks without Weight Symmetry NeurIPS 2023 Correlative Information Maximization Based Biologically Plausible Neural Networks for Correlated Source Separation ICLR 2023 Dynamics of Finite Width Kernel and Prediction Fluctuations in Mean Field Neural Networks NeurIPS 2023 Feature-Learning Networks Are Consistent Across Widths At Realistic Scales NeurIPS 2023 Interneurons accelerate learning dynamics in recurrent neural networks for statistical adaptation ICLR 2023 Learning Curves for Deep Structured Gaussian Feature Models NeurIPS 2023 Learning Curves for Noisy Heterogeneous Feature-Subsampled Ridge Ensembles NeurIPS 2023 Long Sequence Hopfield Memory NeurIPS 2023 Loss Dynamics of Temporal Difference Reinforcement Learning NeurIPS 2023 Neural Circuits for Fast Poisson Compressed Sensing in the Olfactory Bulb NeurIPS 2023 The Influence of Learning Rule on Representation Dynamics in Wide Neural Networks ICLR 2023 The Onset of Variance-Limited Behavior for Networks in the Lazy and Rich Regimes ICLR 2023 Biologically-Plausible Determinant Maximization Neural Networks for Blind Separation of Correlated Sources NeurIPS 2022 Capacity of Group-invariant Linear Readouts from Equivariant Representations: How Many Objects can be Linearly Classified Under All Possible Views? ICLR 2022 Learning Curves for SGD on Structured Features ICLR 2022 Natural gradient enables fast sampling in spiking neural networks NeurIPS 2022 Neural Networks as Kernel Learners: The Silent Alignment Effect ICLR 2022 Self-Consistent Dynamical Field Theory of Kernel Evolution in Wide Neural Networks NeurIPS 2022 Asymptotics of representation learning in finite Bayesian neural networks NeurIPS 2021 Attention Approximates Sparse Distributed Memory NeurIPS 2021 Exact marginal prior distributions of finite Bayesian neural networks NeurIPS 2021 Out-of-Distribution Generalization in Kernel Regression NeurIPS 2021 Associative Memory in Iterated Overparameterized Sigmoid Autoencoders ICML 2020 Minimax Dynamics of Optimally Balanced Spiking Networks of Excitatory and Inhibitory Neurons NeurIPS 2020 Spectrum Dependent Learning Curves in Kernel Regression and Wide Neural Networks ICML 2020 Structured and Deep Similarity Matching via Structured and Deep Hebbian Networks NeurIPS 2019 Manifold-tiling Localized Receptive Fields are Optimal in Similarity-preserving Neural Networks NeurIPS 2018 A Normative Theory of Adaptive Dimensionality Reduction in Neural Networks NeurIPS 2015