Ilija Ilievski

Case Study: Efficient Hyperparameter Optimization for Deep Learning Algorithms.

Automatically searching for optimal hyperparameter configurations is of crucial importance for applying deep learning algorithms in practice. Join the session to learn more about how to implement and what use case is best for its execution.

Ilija is working on developing novel optimization methods for non-convex problems where gradients are unavailable or uninformative. His background is in machine learning (PhD, 2018) and software engineering (MSc, 2014). His main interests lie in solving real-world problems using machine learning and optimization. In the past, he has worked on FX portfolio construction and optimization, interpretable deep learning for finance, image question answering, discourse analysis, movie and news recommender systems, and building complex city models from satellite images and census data.

This website uses cookies to ensure you get the best experience. Learn more