ResearchAlpha Leak

Conferences Topics Top Authors Rankings Browse All

Home/Authors/Cengiz Pehlevan

Cengiz Pehlevan

Topic trends: 32,543 papers · similarity ≥ 0.4 · year ≥ 2024 · Data sourced from Semantic Scholar

34,598 papers | Abstracts: 31,650 (91.5%) | Citations: 34,598 (100.0%) | arXiv: 26,074 (75.4%)

Built: Feb 15, 2026, 1:13 AM AMS

27

papers

734

total citations

papers (27)

Self-Consistent Dynamical Field Theory of Kernel Evolution in Wide Neural Networks

NEURIPS 2022arXiv

Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining

A Dynamical Model of Neural Scaling Laws

Scaling Laws for Precision

Grokking as the transition from lazy to rich training dynamics

Depthwise Hyperparameter Transfer in Residual Networks: Dynamics and Scaling Limit

Feature-Learning Networks Are Consistent Across Widths At Realistic Scales

NEURIPS 2023arXiv

Dynamics of Finite Width Kernel and Prediction Fluctuations in Mean Field Neural Networks

NEURIPS 2023arXiv

Asymptotics of representation learning in finite Bayesian neural networks

NEURIPS 2021arXiv

Attention Approximates Sparse Distributed Memory

NEURIPS 2021arXiv

Long Sequence Hopfield Memory

NEURIPS 2023arXiv

Out-of-Distribution Generalization in Kernel Regression

NEURIPS 2021arXiv

Learning Curves for Deep Structured Gaussian Feature Models

NEURIPS 2023arXiv

The Optimization Landscape of SGD Across the Feature Learning Strength

Deep Linear Network Training Dynamics from Random Initialization: Data, Width, Depth, and Hyperparameter Transfer

Biologically-Plausible Determinant Maximization Neural Networks for Blind Separation of Correlated Sources

NEURIPS 2022arXiv

Minimax Dynamics of Optimally Balanced Spiking Networks of Excitatory and Inhibitory Neurons

NEURIPS 2020arXiv

A solvable model of learning generative diffusion: theory and insights

NEURIPS 2025arXiv

Correlative Information Maximization: A Biologically Plausible Approach to Supervised Deep Neural Networks without Weight Symmetry

NEURIPS 2023arXiv

A Model of Place Field Reorganization During Reward Maximization

No Free Lunch from Random Feature Ensembles: Scaling Laws and Near-Optimality Conditions

Learning Curves for Noisy Heterogeneous Feature-Subsampled Ridge Ensembles

NEURIPS 2023arXiv

Do Mice Grok? Glimpses of Hidden Progress in Sensory Cortex

Exact marginal prior distributions of finite Bayesian neural networks

NEURIPS 2021arXiv

Natural gradient enables fast sampling in spiking neural networks

Neural Circuits for Fast Poisson Compressed Sensing in the Olfactory Bulb

Loss Dynamics of Temporal Difference Reinforcement Learning

NEURIPS 2023arXiv