Publications

Journal Publications

• T. Bui, Josiah Yan and R. E. Turner. (2017). A Unifying Framework for Gaussian Process Pseudo-Point Approximations using Power Expectation Propagation, Journal of Machine Learning Research 18(104), 1-72.

• Gomersall, P., Turner, R.E., Baguley, D.M., Deeks, J.M., Gockel, H.E., and Carlyon, R. P. (2016). Perception of stochastic envelopes by normal-hearing and cochlear-implant listeners Hearing Research 333, 8-24

• M. Afzal, H. Y. Mussa, R. E. Turner, A. Bender, R. C. Glen. (2015) A Multi-label Approach to Target Prediction Taking Ligand Promiscuity into Account, Journal of Cheminformatics, 7(24) 1-14.

• Turner, R. E. and Sahani, M. (2014). Time-frequency analysis as probabilistic inference IEEE Transactions on Signal Processing. Supplementary material available here.

• M. Henniges, R. E. Turner, M. Sahani, J. Eggert, and J. Lucke. (2014) Efficient Occlusive Components, Journal of Machine Learning Research, 15(Aug): 2689−2722.

• V. Leong, M. A. Stone, R. E. Turner, and U. Goswami. (2014) A role for amplitude modulation phase relationships in speech rhythm perception, Journal of the Acoustical Society of America, 136 (1), 366-381.

• H. Christensen, R. E. Turner, S. Hill and S. Godsill. (2013) Rebuilding The Limit Order Book: Sequential Bayesian Inference on Hidden States, Quantitative Finance, 13 (11), 1779-1799.

• Turner, R. E. and Sahani, M. (2011). Demodulation as Probabilistic Inference Transactions on Audio, Speech and Language Processing 19(8), 2398--2411. There is an associated webpage with code and a listing of other related publications here.

• Berkes, P., Turner, R.E., and Sahani, M. (2009). A Structured Model of Video Reproduces Primary Visual Cortical Organisation, PLoS Computational Biology, 5(9)

• Turner, R. E., Walters, T.C., and Patterson, R.D. (2009) Inferring speaker size from speech formant data: A theoretical basis for vocal-tract length estimation, J. Acoust. Soc. Am. 125(4)

• Turner, R.E., and Sahani, M. (2007) A maximum-likelihood interpretation for slow feature analysis, Neural Computation 19(4), 1022-1038.

• Smith, D. R. R., Patterson, R. D., Turner, R. E., Kawahara, H., and Irino, T. (2005). "The processing and perception of size information in speech sounds," J. Acoust. Soc. Am. 117

Refereed Conference Publications

• V. C. Nguyen, Y. Li, T. Bui, and R. E. Turner. (2018) Variational Continual Learning ICLR 2018

• A. G. de G. Matthews, J. Hron, M. Rowland, R. E. Turner, Z. Ghahramani. (2018) Gaussian Process Behaviour in Wide Deep Neural Networks ICLR 2018

• Y. Li and R. E. Turner. (2018) Gradient Estimators for Implicit Models ICLR 2018

• K. Choromanski, M. Rowland, T. Sarlos, V. Sindhwani, R.E. Turner, A. Weller. (2018) The Geometry of Random Features International Conference on Artificial Intelligence and Statistics (AISTATS 2018)

• T. Bui, V. C. Nguyen, and R. E. Turner. (2017) Streaming Sparse Gaussian Process Approximations, Neural Information Processing Systems 2017 NIPS 2017

• S. Gu, T. Lillicrap, Z. Ghahramani, R. E. Turner, B.E. Scholkopf, and S. Levine. (2017). Interpolated Policy Gradient: Merging On-Policy and Off-Policy Gradient Estimation for Deep Reinforcement Learning NIPS 2017

• Jaques, N., Gu, S., Bahdanau D., Hernndez-Lobato J.M., Turner, R.E., Eck, D. (2017) Sequence Tutor: Conservative fine-tuning of sequence generation models with KL-control ICML 2017

• Tripuraneni, N., Rowland, M. Ghahramani, Z., and Turner, R. E. (2017). Magnetic Hamiltonian Monte Carlo ICML 2017

• Gu, S., Lillicrap, T., Ghahramani, Z., Turner, R.E., and Levine, S. (2017). Q-Prop: Sample-Efficient Policy Gradient with an Off-Policy Critic accepted for oral presentation at ICLR

• Navarro, A.K.W., Frellsen, J., and Turner, R.E. (2017). The Multivariate Generalised von Mises: Inference and applications accepted for oral presentation at AAAI2017

• Li, Y., and Turner, R.E. (2016). Rényi Divergence Variational Inference. Advances in Neural Information Processing Systems (28), MIT Press.

• Bui, T., Hernandez-Lobato, J.M., Li, Y., Hernández-Lobato, D., and Turner, R.E. (2016). Deep Gaussian Processes for Regression using Approximate Expectation Propagation. International Conference on Machine Learning 2016

• Hernández-Lobato, J.M., Li, Y., Hernández-Lobato, D., Bui, T., and Turner, R.E. (2016). Black-box α-divergence Minimization. International Conference on Machine Learning 2016

• Matthews, A.G., Hensman, J., Turner, R.E., and Ghahramani, Z. (2016). On Sparse variational methods and the Kullback-Leibler divergence between stochastic processes. Artificial Intelligence and Statistics Conference, AISTATS 2016

• Bui, T., Hernandez-Lobato, J.M., Li, Y., Hernández-Lobato, D., and Turner, R.E. (2015). Training Deep Gaussian Processes using Stochastic Expectation Propagation and Probabilistic Backpropagation. Workshop on Advances in Approximate Bayesian Inference, NIPS 2015

• Hernández-Lobato, D., Hernández-Lobato, J.M., Li, Y., Bui, T., and Turner, R.E. (2015). Stochastic Expectation Propagation for Large Scale Gaussian Process Classification. Workshop on Advances in Approximate Bayesian Inference, NIPS 2015

• Hernández-Lobato, J.M., Li, Y., Hernández-Lobato, D., Bui, T., and Turner, R.E. (2015). Black-box α-divergence Minimization. Workshop on Blackbox Learning and Inference, NIPS 2015

• Tobar, F., Bui, T. and Turner, R.E. (2015). Design of Covariance Functions using Inter-Domain Inducing Variables. Workshop on Time Series, NIPS 2015 Best paper prize winner.

• Li, Y., Hernandez-Lobato, J.M., and Turner, R.E. (2015). Stochastic Expectation Propagation. Advances in Neural Information Processing Systems (27), MIT Press. Awarded spotlight presentation.

• Tobar, F., Bui, T. and Turner, R.E. (2015). Learning Stationary Time Series using Gaussian Processes with Nonparametric Kernels. Advances in Neural Information Processing Systems (27), MIT Press. Awarded spotlight presentation.

• Gu, S., Ghahramani, Z., and Turner, R.E. (2015). Neural Sequential Monte Carlo. Advances in Neural Information Processing Systems (27), MIT Press.

• Gal, Y., and Turner, R.E. (2015). Improving the Gaussian Process Sparse Spectrum Approximation by Representing Uncertainty in Frequency Inputs. Proceedings of The 32nd International Conference on Machine Learning, pp. 655–664.

• Bui, T., and Turner, R.E. (2014). Tree-structured Gaussian Process Approximations. Advances in Neural Information Processing Systems (26), MIT Press. Awarded spotlight presentation.

• Turner, R.E., and Sahani, M. (2012). Decomposing signals into a sum of amplitude and frequency modulated sinusoids using probabilistic inference. Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2173-2176.

• Turner, R.E., and Sahani, M. (2012). Probabilistic amplitude and frequency demodulation. Advances in Neural Information Processing Systems (24), MIT Press. Awarded spotlight presentation.

• Turner, R. E., and Sahani, M. (2010) Statistical inference for single- and multi-band probabilistic amplitude demodulation. In ICASSP'10: Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing.

• Lucke, J., Turner, R.E., Sahani, M., and Henniges, M. (2009). Occlusive Components Analysis. Advances in Neural Information Processing Systems (22), MIT Press.

• Turner, R. E., and Sahani, M. (2008) Modeling Natural Sounds With Modulation Cascade Processes, Advances in Neural Information Processing Systems (21), MIT Press.

• Berkes, P., Turner, R.E., and Sahani, M. (2008) On Sparstity and Overcompleteness in Image Models, Advances in Neural Information Processing Systems (21), MIT Press.

• Turner, R.E., and Sahani, M. (2007) Probabilistic Amplitude Demodulation, Proceedings of the International Conference on Independent Components Analysis 2007 talk. Awarded best student paper.

Thesis

• Turner, R. E., Statistical Models for Natural Sounds, UCL PhD? thesis. There are also a number of related audio demonstrations.

Book chapters

• Turner, R.E. and Sahani, M. (2010) Two problems with variational Expectation Maximisation for time-series models. In: Inference and Learning in Dynamic Models. Eds D. Barber, T. Cemgil and S. Chiappa, Cambridge University Press.

• Turner, R.E., Al-Hames, M.A, Smith, D.R.R., Kawahara, H., Irino, T. and Patterson, R.D. (2006) Vowel normalisation: Time-domain processing of the internal dynamics of speech. In: Dynamics of Speech Production and Perception. Eds P. Divenyi, S. Greenberg and G. Meyer, IOS Press, 153-170.

Unrefereed Conference Publications

• Turner, R. E., Berkes, P., and Sahani, M. (2008) Two problems with variational Expectation Maximisation for time-series models , Presented at the Newton Institute, Cambridge, in the workshop on Inference and Estimation in Probabilistic Time-Series Models (Associated technical report with lots more examples). A video of the talk is available here.

• Turner, R.E., and Sahani, M. (2007) Modeling sounds with modulation cascade processes, Models of Sound and Music Cognition , (NIPS Workshop) talk.

• Turner, R.E., and Sahani, M. (2006) Modeling Natural Sounds with Gaussian Modulation Cascade Processes Advances in Models for Acoustic Processing, (NIPS Workshop) talk.

• Turner, R. E. and Patterson, R.D. (2003). An analysis of the size information in classical formant data: Peterson and Barney (1952) revisited. In: The Acoustical Society of Japan ,Vol 33, No. 9, 585-589.