Oğuz Kaan Yüksel

I am a fourth-year Ph.D candidate @ Theory of Machine Learning, EPFL advised by Nicolas Flammarion. My research focuses on understanding language models from first principles with a focus on mathematical modeling. Here are some keywords that spark my curiosity:

• Generalization: learning-without-mixing, non-i.i.d. learning theory of autoregressive processes, in-context learning, length generalization
• Optimization: incremental learning, saddle to saddle trajectories, implicit bias
• Data: Markovian structure, mixing, stability, mixture processes

Read more about my research.

Short bio. Previously, M.Sc. in Data Science (minor in Mathematics) @ EPFL and B.Sc. in Computer Engineering & Mathematics @ Boğaziçi University. Worked as ML Engineer/Co-founder in NLP and CV applications, infrastructure and model life cycle maintenance. Full-stack web developer. Hobbyist game developer.

For more information, check my CV.