Dr. Adrian Weller

Adrian Weller, Ph.D. is part of the Machine Learning group at Cambridge University in the Computational and Biological Learning Lab.
 
Adrian completed a Ph.D. in computer science in 2014, in the area of machine learning, under the supervision of Prof Tony Jebara after defending his thesis on Methods for Inference in Graphical Models before a committee comprising Profs Alfred Aho, Maria Chudnovsky, Amir Globerson (Hebrew University), Tony Jebara, and David Sontag (NYU). Much of the thesis is based on work in the publications below.
 
Most of his academic research relates to graphical models but he’s also very interested in other areas including: finance, anything on intelligence (natural or artificial), deep learning, reinforcement learning, evolution, Bayesian methods, time series analysis, and methods for big data.
 
Adrian’s papers include Revisiting the Limits of MAP Inference by MWSS on Perfect Graphs, Clamping Variables and Approximate Inference, Approximating the Bethe Partition Function, Understanding the Bethe approximation: When and how can it go wrong?, Network Ranking with Bethe pseudomarginals, On MAP inference by MWSS on perfect graphs, and Bethe Bounds and Approximating the Global Optimum.