Çağatay Yıldız

Room A357

Konemiehentie 2

02150 Espoo, Finland

I’m a doctoral candidate at the Department of Computer Science, Aalto University, Finland. A member of Computational Systems Biology research group, supervised by Harri Lähdesmäki. Before that, I worked with Taylan Cemgil in my Master’s degree at Bogazici University, Istanbul.

I’m trying to understand how continuous-time models can be used in time-series learning, video prediction and reinforcement learning. Curious about the connections with optimal control. My research interests broadly include

  • Neural ordinary differential equations
  • Generative models
  • Reinforcement learning

My name is super easy to pronounce: chaa-tai.

news

Jun 18, 2021 Talk on ODE2VAE at Nordic Probabilistic AI School.
May 8, 2021 ODE-RL accepted to ICML 2021!
Mar 1, 2021 Visiting Thomas Schön’s group at Uppsala University, Sweden.
Feb 1, 2020 Talk on ODE2VAE at Machine Learning Coffee Seminar, here is the video
Jul 25, 2019 ODE2VAE accepted to NeurIPS 2019

selected publications

  1. ICML
    Continuous-time Model-based Reinforcement Learning
    Yildiz, Cagatay, Heinonen, Markus, and Lahdesmaki, Harri
    In International Conference on Machine Learning 2021
  2. NeurIPS
    ODE2VAE: Deep generative second order ODEs with Bayesian neural networks
    Yildiz, Cagatay, Heinonen, Markus, and Lahdesmaki, Harri
    In Advances in Neural Information Processing Systems 2019
  3. ICML
    Learning unknown ODE models with Gaussian processes
    Heinonen, Markus, Yildiz, Cagatay, Mannerström, Henrik, Intosalmi, Jukka, and Lähdesmäki, Harri
    In International Conference on Machine Learning 2018
  4. ICML
    Asynchronous Stochastic Quasi-Newton MCMC for Non-Convex Optimization
    Simsekli, Umut, Yildiz, Cagatay, Nguyen, Than Huy, Cemgil, Taylan, and Richard, Gael
    In International Conference on Machine Learning 2018