Kaan Ozkara
5 papers · 2021–2025 · 4 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🗺️
Taxonomy Completionist
(12)
🐣
Hot Topic Early Bird
Venues
Top co-authors
Research topics
Artificial Intelligence
(4)
Machine Learning
(4)
Deep Learning
(2)
Application Areas
(2)
Core AI
(2)
Learning Paradigms · Artificial Intelligence
(2)
Optimization & Theory · Machine Learning
(2)
Architectures
(1)
Bayesian & Probabilistic
(1)
Learning Paradigms · Machine Learning
(1)
Learning Types
(1)
Optimization & Theory · Deep Learning
(1)
Keywords
federated learning
(3)
personalized model
(2)
convergence analysis
(2)
model quantization
(1)
knowledge distillation
(1)
distributed training
(1)
information geometry
(1)
hierarchical bayesian model
(1)
diffusion model
(1)
empirical baye
(1)
implicit regularization
(1)
statistical heterogeneity
(1)
client-server architecture
(1)
mixed precision training
(1)
stochastic rounding
(1)
hypergradient descent
(1)
validation perplexity
(1)
gpt2
(1)
amsgrad
(1)
avgrad
(1)
Papers
ADEPT: Hierarchical Bayes Approach to Personalized Federated Unsupervised Learning
AISTATS 2025
Stochastic Rounding for LLM Training: Theory and Practice
AISTATS 2025
MADA: Meta-Adaptive Optimizers Through Hyper-Gradient Descent
ICML 2024
A Statistical Framework for Personalized Federated Learning and Estimation: Theory, Algorithms, and Privacy
ICLR 2023
QuPeD: Quantized Personalization via Distillation with Applications to Federated Learning
NeurIPS 2021