Dual space preconditioning for gradient descent by Maddison, CJ, Paulin, D, Teh, YW, Doucet, A

Continuous hierarchical representations with poincaré Variational Auto-Encoder by Mathieu,E, Le Lan, C, Maddison, CJ, Tomioka, R, Teh, YW

Improving lossless compression rates via Monte Carlo bits-back coding by Ruan, Y, Ullrich, K, Severo, D, Townsend, J, Khisti, A, Doucet, A, Makhzani, A, Maddison, CJ