Cengiz Pehlevan

Efficient Principal Subspace Projection of Streaming Data Through Fast Similarity Matching

2018

Big data problems frequently require processing datasets in a streaming fashion, either because all data are available at once but collectively are larger than available memory or because the data intrinsically arrive one data point …

Capacity of Group-invariant Linear Readouts from Equivariant Representations: How Many Objects can be Linearly Classified Under All Possible Views?

2021 · arXiv (Cornell University)

Equivariance has emerged as a desirable property of representations of objects subject to identity-preserving transformations that constitute a group, such as translations and rotations. However, the expressivity of a representation constrained by group equivariance is …

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

2023 · arXiv (Cornell University)

We analyze the dynamics of finite width effects in wide but finite feature learning neural networks. Starting from a dynamical mean field theory description of infinite width deep neural network kernel and prediction dynamics, we …

Partial observation can induce mechanistic mismatches in data-constrained models of neural dynamics

2024 · bioRxiv (Cold Spring Harbor Laboratory)

Abstract One of the central goals of neuroscience is to gain a mechanistic understanding of how the dynamics of neural circuits give rise to their observed function. A popular approach towards this end is to …

Learning curves for deep structured Gaussian feature models*

2024 · Journal of Statistical Mechanics Theory and Experiment

Abstract In recent years, significant attention in deep learning theory has been devoted to analyzing when models that interpolate their training data can still generalize well to unseen examples. Many insights have been gained from …