543 citations · 612 across the 34 of their papers we have counts for
4 papers · 1 filter
PAC-Bayes Bounds for Bandit Problems: A Survey and Experimental Comparison
Hamish Flynn, David Reeb, Melih Kandemir +1
PAC-Bayes has recently re-emerged as an effective theory with which one can derive principled learning algorithms with tight performance guarantees. However, applications of PAC-Ba…
Learning Interacting Dynamical Systems with Latent Gaussian Process ODEs
Çağatay Yıldız, Melih Kandemir, Barbara Rakitsch
We study time uncertainty-aware modeling of continuous-time dynamics of interacting objects. We introduce a new model that decomposes independent dynamics of single objects accurat…
PAC-Bayesian Lifelong Learning For Multi-Armed Bandits
Hamish Flynn, David Reeb, Melih Kandemir +1
We present a PAC-Bayesian analysis of lifelong learning. In the lifelong learning problem, a sequence of learning tasks is observed one-at-a-time, and the goal is to transfer infor…
Continual Learning of Multi-modal Dynamics with External Memory
Abdullah Akgül, Gozde Unal, Melih Kandemir
We study the problem of fitting a model to a dynamical environment when new modes of behavior emerge sequentially. The learning model is aware when a new mode appears, but it canno…