Efstratios Gavves

Mixed Variable Bayesian Optimization with Frequency Modulated Kernels

2021 · arXiv (Cornell University)

The sample efficiency of Bayesian optimization(BO) is often boosted by Gaussian Process(GP) surrogate models. However, on mixed variable spaces, surrogate models other than GPs are prevalent, mainly due to the lack of kernels which can …

Time Does Tell: Self-Supervised Time-Tuning of Dense Image Representations

2023 · arXiv (Cornell University)

Spatially dense self-supervised learning is a rapidly growing problem domain with promising applications for unsupervised segmentation and pretraining for dense downstream tasks. Despite the abundance of temporal data in the form of videos, this information-rich …