1 citations · 1 across the 12 of their papers we have counts for
7 papers · 2 filters
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…