Generalization Bounds for Autoregressive Processes and In-Context Learning
Oğuz Kaan Yüksel, Nicolas Flammarion
In PriGM@EurIPS, 2025
pdf
Incremental Learning of Sparse Attention Patterns in Transformers
Oğuz Kaan Yüksel, Rodrigo Alvarez Lucendo, Nicolas Flammarion
In PriGM@EurIPS, 2025
pdf
On the Sample Complexity of Next-Token Prediction
Oğuz Kaan Yüksel, Nicolas Flammarion
In AISTATS, 2025
pdf
Long-Context Linear System Identification
Oğuz Kaan Yüksel, Mathieu Even, Nicolas Flammarion
In ICLR, 2025
pdf
First-order ANIL provably learns representations despite overparametrization
Oğuz Kaan Yüksel, Etienne Boursier, Nicolas Flammarion
In ICLR, 2024
pdf
LatentCLR: A Contrastive Learning Approach for Unsupervised Discovery of Interpretable Directions
Oğuz Kaan Yüksel*, Enis Simsar*, Ezgi Gülperi Er, Pınar Yanardağ
In ICCV, 2021
pdf code talk website
Semantic Perturbations with Normalizing Flows for Improved Generalization
Oğuz Kaan Yüksel, Sebastian U. Stich, Martin Jaggi, Tatjana Chavdarova
In ICCV, 2021
pdf code talk
Semantic Perturbations with Normalizing Flows for Improved Generalization
Oğuz Kaan Yüksel, Sebastian U. Stich, Martin Jaggi, Tatjana Chavdarova
In INNF+ Workshop, ICML, 2021
pdf code
[Re] Can gradient clipping mitigate label noise?
David Mizrahi, Oğuz Kaan Yüksel, Aiday Marlen Kyzy
In ReScience C, 2021
pdf code
Adversarial Training with Orthogonal Regularization
Oğuz Kaan Yüksel, İnci Meliha Baytaş
In SIU, 2020
pdf
No matching items