3 citations · 5 across the 13 of their papers we have counts for
10 papers · 1 filter
Learnability and Competition in High-Dimensional Multi-Component ICA
Eser Ilke Genc, Samet Demir, Zafer Dogan
Independent Component Analysis (ICA) is a foundational tool for unsupervised representation learning, yet its high-dimensional theory remains largely limited to single-component re…
Learning Beyond the Gaussian Data: Learning Dynamics of Neural Networks on an Expressive and Cumulant-Controllable Data Model
Onat Ure, Samet Demir, Zafer Dogan
We study the effect of high-order statistics of data on the learning dynamics of neural networks (NNs) by using a moment-controllable non-Gaussian data model. Considering the expre…
Implicitly Normalized Online PCA: A Regularized Algorithm with Exact High-Dimensional Dynamics
Samet Demir, Zafer Dogan
Many online learning algorithms, including classical online PCA methods, enforce explicit normalization steps that discard the evolving norm of the parameter vector. We show that t…
Optimal Attention Temperature Improves the Robustness of In-Context Learning under Distribution Shift in High Dimensions
Samet Demir, Zafer Dogan
Pretrained Transformers can perform in-context learning (ICL) from a few demonstrations, but this ability can fail sharply when the test distribution differs from pretraining, a co…
How Data Mixing Shapes In-Context Learning: Asymptotic Equivalence for Transformers with MLPs
Samet Demir, Zafer Dogan
Pretrained Transformers demonstrate remarkable in-context learning (ICL) capabilities, enabling them to adapt to new tasks from demonstrations without parameter updates. However, t…
Asymptotic Study of In-context Learning with Random Transformers through Equivalent Models
Samet Demir, Zafer Dogan
We study the in-context learning (ICL) capabilities of pretrained Transformers in the setting of nonlinear regression. Specifically, we focus on a random Transformer with a nonline…
Benefits of Online Tilted Empirical Risk Minimization: A Case Study of Outlier Detection and Robust Regression
Yigit E. Yildirim, Samet Demir, Zafer Dogan
Empirical Risk Minimization (ERM) is a foundational framework for supervised learning but primarily optimizes average-case performance, often neglecting fairness and robustness con…
Learning Rate Should Scale Inversely with High-Order Data Moments in High-Dimensional Online Independent Component Analysis
M. Oguzhan Gultekin, Samet Demir, Zafer Dogan
We investigate the impact of high-order moments on the learning dynamics of an online Independent Component Analysis (ICA) algorithm under a high-dimensional data model composed of…
Asymptotic Analysis of Two-Layer Neural Networks after One Gradient Step under Gaussian Mixtures Data with Structure
Samet Demir, Zafer Dogan
In this work, we study the training and generalization performance of two-layer neural networks (NNs) after one gradient descent step under structured data modeled by Gaussian mixt…
Input-Label Correlation Governs a Linear-to-Nonlinear Transition in Random Features under Spiked Covariance
Samet Demir, Zafer Dogan
Random feature models (RFMs), two-layer networks with a randomly initialized fixed first layer and a trained linear readout, are among the simplest nonlinear predictors. Prior asym…