4 citations · 7 across the 3 of their papers we have counts for
3 papers
stat.CO2017★ 4 cited
Spontaneous Symmetry Breaking in Neural Networks
Ricky Fok, Aijun An, Xiaogang Wang
We propose a framework to understand the unprecedented performance and robustness of deep neural networks using field theory. Correlations between the weights within the same layer…
stat.CO2017★ 3 cited
Optimization assisted MCMC
Ricky Fok, Aijun An, Xiaogang Wang
Markov Chain Monte Carlo (MCMC) sampling methods are widely used but often encounter either slow convergence or biased sampling when applied to multimodal high dimensional distribu…
stat.CO2015
Geodesic and Contour Optimization Using Conformal Mapping
Ricky Fok, Aijun An, Xiaogong Wang
We propose a novel optimization algorithm for continuous functions using geodesics and contours under conformal mapping.The algorithm can find multiple optima by first following a…