Samet Demir

According to our database, Samet Demir authored at least 13 papers between 2019 and 2026.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2026

Learning Beyond the Gaussian Data: Learning Dynamics of Neural Networks on an Expressive and Cumulant-Controllable Data Model.

Onat Ure, Samet Demir, Zafer Dogan

CoRR, February, 2026

2025

Implicitly Normalized Online PCA: A Regularized Algorithm with Exact High-Dimensional Dynamics.

Samet Demir, Zafer Dogan

CoRR, December, 2025

Optimal Attention Temperature Enhances In-Context Learning under Distribution Shift.

Samet Demir, Zafer Dogan

CoRR, November, 2025

How Data Mixing Shapes In-Context Learning: Asymptotic Equivalence for Transformers with MLPs.

Samet Demir, Zafer Dogan

CoRR, October, 2025

Benefits of Online Tilted Empirical Risk Minimization: A Case Study of Outlier Detection and Robust Regression.

Yigit E. Yildirim, Samet Demir, Zafer Dogan

Proceedings of the 35th IEEE International Workshop on Machine Learning for Signal Processing, 2025

Learning Rate Should Scale Inversely with High-Order Data Moments in High-Dimensional Online Independent Component Analysis.

M. Oguzhan Gultekin, Samet Demir, Zafer Dogan

Proceedings of the 35th IEEE International Workshop on Machine Learning for Signal Processing, 2025

Asymptotic Study of in-Context Learning with Random Transformers Through Equivalent Models.

Samet Demir, Zafer Dogan

Proceedings of the 35th IEEE International Workshop on Machine Learning for Signal Processing, 2025

Asymptotic Analysis of Two-Layer Neural Networks after One Gradient Step under Gaussian Mixtures Data with Structure.

Samet Demir, Zafer Dogan

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

2024

Random Features Outperform Linear Models: Effect of Strong Input-Label Correlation in Spiked Covariance Data.

Samet Demir, Zafer Dogan

CoRR, 2024

Studying Generalization Performance of Random Feature Model through Equivalent Models.

Samet Demir, Zafer Dogan

Proceedings of the 32nd Signal Processing and Communications Applications Conference, 2024

2023

Optimal Nonlinearities Improve Generalization Performance of Random Features.

Samet Demir, Zafer Dogan

Proceedings of the Asian Conference on Machine Learning, 2023

2020

DeepSmartFuzzer: Reward Guided Test Generation For Deep Learning.

Samet Demir, Hasan Ferit Eniser, Alper Sen

Proceedings of the Workshop on Artificial Intelligence Safety 2020 co-located with the 29th International Joint Conference on Artificial Intelligence and the 17th Pacific Rim International Conference on Artificial Intelligence (IJCAI-PRICAI 2020), 2020

2019

Neural Academic Paper Generation.

Samet Demir, Uras Mutlu, Özgür Özdemir

CoRR, 2019