Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
162 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Variational Inference of Joint Models using Multivariate Gaussian Convolution Processes (1903.03867v1)

Published 9 Mar 2019 in stat.ML and cs.LG

Abstract: We present a non-parametric prognostic framework for individualized event prediction based on joint modeling of both longitudinal and time-to-event data. Our approach exploits a multivariate Gaussian convolution process (MGCP) to model the evolution of longitudinal signals and a Cox model to map time-to-event data with longitudinal data modeled through the MGCP. Taking advantage of the unique structure imposed by convolved processes, we provide a variational inference framework to simultaneously estimate parameters in the joint MGCP-Cox model. This significantly reduces computational complexity and safeguards against model overfitting. Experiments on synthetic and real world data show that the proposed framework outperforms state-of-the art approaches built on two-stage inference and strong parametric assumptions.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (42)
  1. Sparse convolved gaussian processes for multi-output regression. In Advances in neural information processing systems, pp. 57–64, 2009.
  2. Computationally efficient convolved multiple output gaussian processes. Journal of Machine Learning Research, 12(May):1459–1500, 2011.
  3. Efficient multioutput gaussian processes through variational inducing kernels. In Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, pp.  25–32, 2010.
  4. A comparison of smoothing techniques for cd4 data measured with error in a time-dependent cox proportional hazards model. Statistics in medicine, 17(18):2061–2077, 1998.
  5. Cheng, C. Multi-scale gaussian process experts for dynamic evolution prediction of complex systems. Expert Systems with Applications, 99:25–31, 2018.
  6. Cox, D. R. Regression models and life-tables. Journal of the Royal Statistical Society: Series B (Methodological), 34(2):187–202, 1972.
  7. Flexible parametric joint modelling of longitudinal and survival data. Statistics in Medicine, 31(30):4456–4471, 2012.
  8. Joint modeling of longitudinal and survival data. The Stata Journal, 13(1):165–184, 2013.
  9. Deep gaussian processes. In Artificial Intelligence and Statistics, pp.  207–215, 2013.
  10. isurvive: An interpretable, event-time prediction model for mhealth. In International Conference on Machine Learning, pp. 970–979, 2017.
  11. Multitask gaussian processes for multivariate physiological time-series analysis. IEEE Transactions on Biomedical Engineering, 62(1):314–322, 2015.
  12. Gaussian processes for survival analysis. In Advances in Neural Information Processing Systems, pp. 5021–5029, 2016.
  13. Cloud-enabled prognosis for manufacturing. CIRP annals, 64(2):749–772, 2015.
  14. A general repair, proportional-hazards, framework to model complex repairable systems. IEEE Transactions on Reliability, 52(1):26–32, 2003.
  15. Fast kernel approximations for latent force models and convolved multiple-output gaussian processes. arXiv preprint arXiv:1805.07460, 2018.
  16. Simultaneous variable selection for joint models of longitudinal and survival outcomes. Biometrics, 71(1):178–187, 2015.
  17. The statistical analysis of failure time data, volume 360. John Wiley & Sons, 2011.
  18. Variational inference for gaussian process models for survival analysis. Uncertainty in Artificial Intelligence, 2018.
  19. Nonparametric-condition-based remaining useful life prediction incorporating external factors. IEEE Transactions on Reliability, 67(1):41–52, 2018a.
  20. Nonparametric modeling and prognosis of condition monitoring signals using multivariate gaussian convolution processes. Technometrics, 60(4):484–496, 2018b.
  21. A data-level fusion model for developing composite health indices for degradation modeling and prognostic analysis. IEEE Transactions on Automation Science and Engineering, 10(3):652–664, 2013.
  22. Joint models with multiple longitudinal outcomes and a time-to-event outcome. arXiv preprint arXiv:1808.07719, 2018.
  23. Heterogeneous multi-output gaussian process prediction. arXiv preprint arXiv:1805.07633, 2018.
  24. Machine performance degradation assessment and remaining useful life prediction using proportional hazard model and support vector machine. Mechanical Systems and Signal Processing, 32:320–330, 2012.
  25. Joint latent class models for longitudinal and time-to-event data: A review. Statistical methods in medical research, 23(1):74–90, 2014.
  26. Rizopoulos, D. Dynamic predictions and prospective accuracy in joint models for longitudinal and time-to-event data. Biometrics, 67(3):819–829, 2011.
  27. Rizopoulos, D. Joint models for longitudinal and time-to-event data: With applications in R. Chapman and Hall/CRC, 2012.
  28. Dynamic predictions with time-dependent covariates in survival analysis using joint modeling and landmarking. Biometrical Journal, 59(6):1261–1276, 2017.
  29. Rosenberg, P. S. Hazard function estimation using b-splines. Biometrics, pp.  874–887, 1995.
  30. Ruppert, D. Selecting the number of knots for penalized splines. Journal of computational and graphical statistics, 11(4):735–757, 2002.
  31. Turbofan engine degradation simulation data set, 2008. data retrieved from NASA Ames Prognostics Data Repository, https://ti.arc.nasa.gov/tech/dash/groups/pcoe/prognostic-data-repository/.
  32. Sparse gaussian processes using pseudo-inputs. In Advances in neural information processing systems, pp. 1257–1264, 2006.
  33. Scalable joint models for reliable uncertainty-aware event prediction. IEEE transactions on pattern analysis and machine intelligence, 40(8):1948–1963, 2018.
  34. Bayesian gaussian process latent variable model. In Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, pp.  844–851, 2010.
  35. Modeling the relationship of survival to longitudinal data measured with error. applications to survival and cd4 counts in patients with aids. Journal of the American Statistical Association, 90(429):27–37, 1995.
  36. Analysis of longitudinal and survival data: joint modeling, inference methods, and issues. Journal of Probability and Statistics, 2012, 2012.
  37. A joint model for survival and longitudinal data measured with error. Biometrics, pp.  330–339, 1997.
  38. Multiple sensor data fusion for degradation modeling and prognostics under multiple operational conditions. IEEE Transactions on Reliability, 65(3):1416–1426, 2016.
  39. Joint longitudinal-survival-cure models and their application to prostate cancer. Statistica Sinica, pp.  835–862, 2004.
  40. Variational dependent multi-output gaussian process dynamical systems. The Journal of Machine Learning Research, 17(1):4134–4169, 2016.
  41. Remaining useful life prediction of individual units subject to hard failure. IIE Transactions, 46(10):1017–1030, 2014.
  42. Bayesian influence measures for joint models for longitudinal and survival data. Biometrics, 68(3):954–964, 2012.
Citations (13)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now