Kaan Ozkara

According to our database, Kaan Ozkara authored at least 13 papers between 2021 and 2026.

Collaborative distances:

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

2026

Directional Alignment Mitigates Reward Hacking in Reinforcement Learning for Language Models.

Wenlong Deng, Jiaji Huang, Kaan Ozkara, Yushu Li, Christos Thrampoulidis, Xiaoxiao Li, Youngsuk Park

CoRR, May, 2026

2025

MuonBP: Faster Muon via Block-Periodic Orthogonalization.

Ahmed Khaled, Kaan Ozkara, Tao Yu, Mingyi Hong, Youngsuk Park

CoRR, October, 2025

MEL: Multi-level Ensemble Learning for Resource-Constrained Environments.

Krishna Praneet Gudipaty, Walid A. Hanafy, Kaan Ozkara, Qianlin Liang, Jesse Milzman, Prashant J. Shenoy, Suhas N. Diggavi

CoRR, June, 2025

SPIRE: Conditional Personalization for Federated Diffusion Generative Models.

Kaan Ozkara, Ruida Zhou, Suhas N. Diggavi

CoRR, June, 2025

Stochastic Rounding for LLM Training: Theory and Practice.

Kaan Ozkara, Tao Yu, Youngsuk Park

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2025

ADEPT: Hierarchical Bayes Approach to Personalized Federated Unsupervised Learning.

Kaan Ozkara, Bruce Huang, Ruida Zhou, Suhas N. Diggavi

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2025

2024

Hierarchical Bayes Approach to Personalized Federated Unsupervised Learning.

Kaan Ozkara, Bruce Huang, Ruida Zhou, Suhas N. Diggavi

CoRR, 2024

MADA: Meta-Adaptive Optimizers Through Hyper-Gradient Descent.

Kaan Ozkara, Can Karakus, Parameswaran Raman, Mingyi Hong, Shoham Sabach, Branislav Kveton, Volkan Cevher

Proceedings of the Forty-first International Conference on Machine Learning, 2024

2023

Personalized PCA for Federated Heterogeneous Data.

Kaan Ozkara, Bruce Huang, Suhas N. Diggavi

Proceedings of the IEEE International Symposium on Information Theory, 2023

A Statistical Framework for Personalized Federated Learning and Estimation: Theory, Algorithms, and Privacy.

Kaan Ozkara, Antonious M. Girgis, Deepesh Data, Suhas N. Diggavi

Proceedings of the Eleventh International Conference on Learning Representations, 2023

2022

A Generative Framework for Personalized Learning and Estimation: Theory, Algorithms, and Privacy.

Kaan Ozkara, Antonious M. Girgis, Deepesh Data, Suhas N. Diggavi

CoRR, 2022

2021

QuPeL: Quantized Personalization with Applications to Federated Learning.

Kaan Ozkara, Navjot Singh, Deepesh Data, Suhas N. Diggavi

CoRR, 2021

QuPeD: Quantized Personalization via Distillation with Applications to Federated Learning.

Kaan Ozkara, Navjot Singh, Deepesh Data, Suhas N. Diggavi

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021