collaborators

6 papers

cs.LG2026

Score Broadcast and Decorrelation: A General Framework for Broadcast-Based Credit Assignment

Mustafa Uzun, Mete Erdogan, Cengiz Pehlevan +1

We introduce Score Broadcast and Decorrelation (SBD), a principled framework for broadcast-based credit assignment for general families of differentiable losses. Error broadcast is…

cond-mat.dis-nn2026

Spectral Dynamics in Deep Networks: Feature Learning, Outlier Escape, and Learning Rate Transfer

Clarissa Lauditi, Cengiz Pehlevan, Blake Bordelon

We study the evolution of hidden-weight spectra in wide neural networks trained by (stochastic) gradient descent. We develop a two-level dynamical mean-field theory (DMFT) that joi…

cs.NE2026

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

Bariscan Bozkurt, Cengiz Pehlevan, Alper T Erdogan

The backpropagation algorithm has experienced remarkable success in training large-scale artificial neural networks; however, its biological plausibility has been strongly criticiz…

cs.LG2026

Pixel-Based Similarities as an Alternative to Neural Data for Improving Convolutional Neural Network Adversarial Robustness

Elie Attias, Cengiz Pehlevan, Dina Obeid

Convolutional Neural Networks (CNNs) excel in many visual tasks but remain susceptible to adversarial attacks-imperceptible perturbations that degrade performance. Prior research r…

cs.LG2026

Demystifying LLM-as-a-Judge: Analytically Tractable Model for Inference-Time Scaling

Indranil Halder, Cengiz Pehlevan

Recent developments in large language models have shown advantages in reallocating a notable share of computational resource from training time to inference time. However, the prin…

cs.LG2025

Error Broadcast and Decorrelation as a Potential Artificial and Natural Learning Mechanism

Mete Erdogan, Cengiz Pehlevan, Alper T. Erdogan

We introduce Error Broadcast and Decorrelation (EBD), a novel learning framework for neural networks that addresses credit assignment by directly broadcasting output errors to indi…