{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,19]],"date-time":"2025-03-19T15:46:08Z","timestamp":1742399168250},"reference-count":98,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2024,8,6]],"date-time":"2024-08-06T00:00:00Z","timestamp":1722902400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,8,6]],"date-time":"2024-08-06T00:00:00Z","timestamp":1722902400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Stat Comput"],"published-print":{"date-parts":[[2024,10]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Variational autoencoders (VAEs) are popular likelihood-based generative models which can be efficiently trained by maximising an evidence lower bound. There has been much progress in improving the expressiveness of the variational distribution to obtain tighter variational bounds and increased generative performance. Whilst previous work has leveraged Markov chain Monte Carlo methods for constructing variational densities, gradient-based methods for adapting the proposal distributions for deep latent variable models have received less attention. This work suggests an entropy-based adaptation for a short-run metropolis-adjusted Langevin or Hamiltonian Monte Carlo (HMC) chain while optimising a tighter variational bound to the log-evidence. Experiments show that this approach yields higher held-out log-likelihoods as well as improved generative metrics. Our implicit variational density can adapt to complicated posterior geometries of latent hierarchical representations arising in hierarchical VAEs.<\/jats:p>","DOI":"10.1007\/s11222-024-10481-x","type":"journal-article","created":{"date-parts":[[2024,8,6]],"date-time":"2024-08-06T16:02:44Z","timestamp":1722960164000},"update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Learning variational autoencoders via MCMC speed measures"],"prefix":"10.1007","volume":"34","author":[{"given":"Marcel","family":"Hirt","sequence":"first","affiliation":[]},{"given":"Vasileios","family":"Kreouzis","sequence":"additional","affiliation":[]},{"given":"Petros","family":"Dellaportas","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,8,6]]},"reference":[{"key":"10481_CR1","unstructured":"Abadi, M., Barham, P., Chen, J., et\u00a0al: Tensorflow: a system for large-scale machine learning. In: 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI 16), pp. 265\u2013283 (2016)"},{"key":"10481_CR2","doi-asserted-by":"crossref","unstructured":"Altschuler, J.M., Chewi, S.: Faster high-accuracy log-concave sampling via algorithmic warm starts. In: 2023 IEEE 64th Annual Symposium on Foundations of Computer Science (FOCS). IEEE, pp. 2169\u20132176 (2023)","DOI":"10.1109\/FOCS57990.2023.00134"},{"key":"10481_CR3","volume-title":"Gradient flows: in Metric Spaces and in the Space of Probability Measures","author":"L Ambrosio","year":"2005","unstructured":"Ambrosio, L., Gigli, N., Savar\u00e9, G.: Gradient flows: in Metric Spaces and in the Space of Probability Measures. Springer, Berlin (2005)"},{"issue":"3","key":"10481_CR4","doi-asserted-by":"publisher","first-page":"269","DOI":"10.1111\/j.1467-9868.2009.00736.x","volume":"72","author":"C Andrieu","year":"2010","unstructured":"Andrieu, C., Doucet, A., Holenstein, R.: Particle Markov Chain Monte Carlo methods. J. R. Stat. Soc. Ser. B (Stat. Methodol.) 72(3), 269\u2013342 (2010)","journal-title":"J. R. Stat. Soc. Ser. B (Stat. Methodol.)"},{"key":"10481_CR5","first-page":"480","volume":"34","author":"J Aneja","year":"2021","unstructured":"Aneja, J., Schwing, A., Kautz, J., et al.: A contrastive learning approach for training Variational Autoencoder priors. Adv. Neural. Inf. Process. Syst. 34, 480\u2013493 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"10481_CR6","unstructured":"Barber, D., Bishop, C.M. Ensemble learning for multi-layer networks. In: Advances in Neural Information Processing Systems, pp. 395\u2013401 (1998)"},{"key":"10481_CR7","unstructured":"Behrmann, J., Grathwohl, W., Chen, R.T., et\u00a0al: Invertible residual networks. In: International Conference on Machine Learning, pp. 573\u2013582 (2019)"},{"key":"10481_CR8","unstructured":"Bi\u0144kowski, M., Sutherland, D.J., Arbel, M., et\u00a0al: Demystifying MMD GANs. (2018) arXiv:1801.01401"},{"key":"10481_CR9","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1017\/S0962492917000101","volume":"27","author":"N Bou-Rabee","year":"2018","unstructured":"Bou-Rabee, N., Sanz-Serna, J.M.: Geometric integrators and the Hamiltonian Monte Carlo method. Acta Numer 27, 113\u2013206 (2018)","journal-title":"Acta Numer"},{"key":"10481_CR10","unstructured":"Burda, Y., Grosse, R., Salakhutdinov, R.: Importance weighted autoencoders. (2015) arXiv:1509.00519"},{"key":"10481_CR11","unstructured":"Caterini, A.L., Doucet, A., Sejdinovic, D.: Hamiltonian variational auto-encoder. In: Advances in Neural Information Processing Systems, pp. 8167\u20138177 (2018)"},{"key":"10481_CR12","unstructured":"Chen, T.Q., Behrmann, J., Duvenaud, D.K., et\u00a0al: Residual flows for invertible generative modeling. In: Advances in Neural Information Processing Systems, pp. 9913\u20139923 (2019a)"},{"key":"10481_CR13","unstructured":"Chen, Y., Gatmiry, K.: A simple proof of the mixing of metropolis-adjusted langevin algorithm under smoothness and isoperimetry (2023). arXiv:2304.04095"},{"key":"10481_CR14","unstructured":"Chen, Y., Dwivedi, R., Wainwright, M.J., et\u00a0al: Fast mixing of metropolized Hamiltonian Monte Carlo: benefits of multi-step gradients (2019b). arXiv:1905.12247"},{"key":"10481_CR15","unstructured":"Chewi, S., Lu, C., Ahn, K., et\u00a0al: Optimal dimension dependence of the metropolis-adjusted langevin algorithm. In: Conference on Learning Theory, PMLR, pp. 1260\u20131300 (2021)"},{"key":"10481_CR16","unstructured":"Child, R.: Very deep VAEs generalize autoregressive models and can outperform them on images. In: International Conference on Learning Representations (2021)"},{"issue":"1","key":"10481_CR17","first-page":"1573","volume":"19","author":"B Dai","year":"2018","unstructured":"Dai, B., Wang, Y., Aston, J., et al.: Connections with robust PCA and the role of emergent sparsity in variational autoencoder models. J. Mach. Learn. Res. 19(1), 1573\u20131614 (2018)","journal-title":"J. Mach. Learn. Res."},{"key":"10481_CR18","unstructured":"Dilokthanakul, N., Mediano, P.A., Garnelo, M., et\u00a0al: Deep unsupervised clustering with Gaussian mixture Variational Autoencoders (2016). arXiv:1611.02648"},{"key":"10481_CR19","unstructured":"Dockhorn, T., Vahdat, A., Kreis, K.: Score-based generative modeling with critically-damped langevin diffusion. In: International Conference on Learning Representations (2021)"},{"key":"10481_CR20","unstructured":"Du, Y., Mordatch, I.: Implicit generation and modeling with energy based models. Advances in Neural Information Processing Systems 32, pp. 3608\u20133618 (2019)"},{"key":"10481_CR21","unstructured":"Durmus, A., Moulines, E., Saksman, E.: On the convergence of Hamiltonian Monte Carlo (2017). arXiv:1705.00166"},{"issue":"183","key":"10481_CR22","first-page":"1","volume":"20","author":"R Dwivedi","year":"2019","unstructured":"Dwivedi, R., Chen, Y., Wainwright, M.J., et al.: Log-concave sampling: metropolis-hastings algorithms are fast. J. Mach. Learn. Res. 20(183), 1\u201342 (2019)","journal-title":"J. Mach. Learn. Res."},{"key":"10481_CR23","unstructured":"Falck, F., Williams, C., Danks, D., et\u00a0al: A multi-resolution framework for U-Nets with applications to hierarchical VAEs. In: Advances in Neural Information Processing Systems (2022)"},{"key":"10481_CR24","unstructured":"Finke, A., Thiery, A.H.: On importance-weighted autoencoders (2019). arXiv:1907.10477"},{"key":"10481_CR25","unstructured":"Geffner, T., Domke, J.: On the difficulty of unbiased alpha divergence minimization. In: International Conference on Machine Learning, PMLR, pp. 3650\u20133659 (2021)"},{"key":"10481_CR26","unstructured":"Guo, F., Wang, X., Fan, K., et\u00a0al: Boosting variational inference (2016). arXiv:1611.05559"},{"issue":"3","key":"10481_CR27","doi-asserted-by":"publisher","first-page":"1162","DOI":"10.1137\/21M1450604","volume":"10","author":"P Hagemann","year":"2022","unstructured":"Hagemann, P., Hertrich, J., Steidl, G.: Stochastic normalizing flows for inverse problems: a Markov Chains viewpoint. SIAM\/ASA J. Uncertain. Quantif. 10(3), 1162\u20131190 (2022)","journal-title":"SIAM\/ASA J. Uncertain. Quantif."},{"key":"10481_CR28","doi-asserted-by":"publisher","first-page":"399","DOI":"10.1017\/S0962492902000144","volume":"12","author":"E Hairer","year":"2003","unstructured":"Hairer, E., Lubich, C., Wanner, G.: Geometric numerical integration illustrated by the St\u00f6rmer\u2013Verlet method. Acta Numer 12, 399\u2013450 (2003)","journal-title":"Acta Numer"},{"key":"10481_CR29","unstructured":"Han, S., Liao, X., Dunson, D., et\u00a0al: Variational Gaussian copula inference. In: Artificial Intelligence and Statistics, pp. 829\u2013838 (2016)"},{"key":"10481_CR30","doi-asserted-by":"crossref","unstructured":"Han, T., Lu, Y., Zhu, S.C., et\u00a0al: Alternating back-propagation for generator network. In: Proceedings of the AAAI Conference on Artificial Intelligence (2017)","DOI":"10.1609\/aaai.v31i1.10902"},{"key":"10481_CR31","unstructured":"Han, T., Zhang, J., Wu, Y.N.: From EM-projections to variational auto-encoder. In: NeurIPS 2020 Workshop: Deep Learning through Information Geometry (2020)"},{"key":"10481_CR32","unstructured":"Hernandez-Lobato, J., Li, Y., Rowland, M., et\u00a0al: Black-box alpha divergence minimization. In: International Conference on Machine Learning, PMLR, pp. 1511\u20131520 (2016)"},{"key":"10481_CR33","first-page":"28482","volume":"34","author":"M Hirt","year":"2021","unstructured":"Hirt, M., Titsias, M., Dellaportas, P.: Entropy-based adaptive Hamiltonian Monte Carlo. Adv. Neural. Inf. Process. Syst. 34, 28482\u201328495 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"10481_CR34","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Adv. Neural. Inf. Process. Syst. 33, 6840\u20136851 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"10481_CR35","unstructured":"Hoffman, M, Sountsov, P., Dillon, J.V., et\u00a0al: Neutra-lizing bad geometry in Hamiltonian Monte Carlo using neural transport (2019). arXiv:1903.03704"},{"key":"10481_CR36","unstructured":"Hoffman, M.D.: Learning deep latent Gaussian models with Markov chain Monte Carlo. In: International Conference on Machine Learning, pp. 1510\u20131519 (2017)"},{"issue":"1","key":"10481_CR37","first-page":"1593","volume":"15","author":"MD Hoffman","year":"2014","unstructured":"Hoffman, M.D., Gelman, A.: The No-U-Turn sampler: adaptively setting path lengths in Hamiltonian Monte Carlo. J. Mach. Learn. Res. 15(1), 1593\u20131623 (2014)","journal-title":"J. Mach. Learn. Res."},{"key":"10481_CR38","unstructured":"Hoffman, M.D., Johnson, M.J.: Elbo surgery: yet another way to carve up the variational evidence lower bound. In: Workshop in Advances in Approximate Bayesian Inference, NIPS (2016)"},{"key":"10481_CR39","doi-asserted-by":"crossref","unstructured":"Jiang, Z., Zheng, Y., Tan, H., et\u00a0al: Variational deep embedding: an unsupervised and generative approach to clustering. In: Proceedings of the 26th International Joint Conference on Artificial Intelligence, pp. 1965\u20131972 (2017)","DOI":"10.24963\/ijcai.2017\/273"},{"key":"10481_CR40","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding Variational Bayes. In: Proceedings of the 2nd International Conference on Learning Representations (ICLR) (2014)"},{"key":"10481_CR41","unstructured":"Kingma, D.P., Salimans, T., Jozefowicz, R., et\u00a0al: Improved variational inference with inverse autoregressive flow. In: Advances in Neural Information Processing Systems, pp. 4743\u20134751 (2016)"},{"key":"10481_CR42","unstructured":"Klushyn, A., Chen, N., Kurle, R., et al: Learning hierarchical priors in VAEs. Advances in Neural Information Processing Systems 32, pp. 2870\u20132879 (2019)"},{"key":"10481_CR43","unstructured":"Kuzina, A., Welling, M., Tomczak, J.M.: Alleviating adversarial attacks on variational autoencoders with MCMC. In: Advances in Neural Information Processing Systems (2022)"},{"key":"10481_CR44","unstructured":"Lee, Y.T., Shen, R., Tian, K.: Logsmooth gradient concentration and tighter runtimes for metropolized Hamiltonian Monte Carlo. In: Conference on Learning Theory, PMLR, pp. 2565\u20132597 (2020)"},{"key":"10481_CR45","first-page":"18812","volume":"34","author":"YT Lee","year":"2021","unstructured":"Lee, Y.T., Shen, R., Tian, K.: Lower bounds on metropolized sampling methods for well-conditioned distributions. Adv. Neural. Inf. Process. Syst. 34, 18812\u201318824 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"10481_CR46","unstructured":"Levy, D., Hoffman, M.D., Sohl-Dickstein, J.: Generalizing Hamiltonian Monte Carlo with neural networks. In: International Conference on Learning Representations (2018)"},{"key":"10481_CR47","unstructured":"Li, C., Wang, Y., Li, W., et\u00a0al Forward chi-squared divergence based variational importance sampling (2023). arXiv:2311.02516"},{"key":"10481_CR48","doi-asserted-by":"crossref","unstructured":"Li, Z., Chen, Y., Sommer, F.T.P: A neural network MCMC sampler that maximizes proposal entropy (2020). arXiv:2010.03587","DOI":"10.3390\/e23030269"},{"issue":"4A","key":"10481_CR49","doi-asserted-by":"publisher","first-page":"3109","DOI":"10.3150\/18-BEJ1083","volume":"25","author":"S Livingstone","year":"2019","unstructured":"Livingstone, S., Betancourt, M., Byrne, S., et al.: On the geometric ergodicity of Hamiltonian Monte Carlo. Bernoulli 25(4A), 3109\u20133138 (2019)","journal-title":"Bernoulli"},{"key":"10481_CR50","unstructured":"Locatello, F., Dresdner, G., Khanna, R., et\u00a0al Boosting black box variational inference. In: Advances in Neural Information Processing Systems, pp. 3401\u20133411 (2018)"},{"key":"10481_CR51","unstructured":"Louizos, C., Welling, M.: Structured and efficient variational deep learning with matrix Gaussian posteriors. In: Proceedings of the 33rd International Conference on Machine Learning (2016)"},{"key":"10481_CR52","unstructured":"Louizos, C., Welling, M.: Multiplicative normalizing flows for variational bayesian neural networks. In: International Conference on Machine Learning, pp. 2218\u20132227 (2017)"},{"key":"10481_CR53","unstructured":"Lucas, J., Tucker, G., Grosse, R.B., et\u00a0al: Don\u2019t blame the ELBO! a linear VAE perspective on posterior collapse. In: Advances in Neural Information Processing Systems, pp. 9408\u20139418 (2019)"},{"key":"10481_CR54","first-page":"6551","volume":"32","author":"L Maal\u00f8e","year":"2019","unstructured":"Maal\u00f8e, L., Fraccaro, M., Li\u00e9vin, V., et al.: Biva: a very deep hierarchy of latent variables for generative modeling. Adv. Neural. Inf. Process. Syst. 32, 6551\u20136562 (2019)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"10481_CR55","unstructured":"Mangoubi, O., Vishnoi, N.K.: Nonconvex sampling with the metropolis-adjusted langevin algorithm. In: Conference on Learning Theory, PMLR, pp. 2259\u20132293 (2019)"},{"key":"10481_CR56","unstructured":"Mescheder, L., Nowozin, S., Geiger, A.: Adversarial variational Bayes: unifying variational autoencoders and generative adversarial networks. In: International Conference on Machine learning (ICML) (2017)"},{"key":"10481_CR57","unstructured":"Molchanov, D., Kharitonov, V., Sobolev, A., et\u00a0al: Doubly semi-implicit variational inference. In: The 22nd International Conference on Artificial Intelligence and Statistics, PMLR, pp. 2593\u20132602 (2019)"},{"issue":"1","key":"10481_CR58","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1007\/s10107-007-0149-x","volume":"120","author":"Y Nesterov","year":"2009","unstructured":"Nesterov, Y.: Primal-dual subgradient methods for convex problems. Math. Program. 120(1), 221\u2013259 (2009)","journal-title":"Math. Program."},{"key":"10481_CR59","doi-asserted-by":"crossref","unstructured":"Nijkamp, E., Pang, B., Han, T., et\u00a0al: Learning multi-layer latent variable model via variational optimization of short run MCMC for approximate inference. In: European Conference on Computer Vision. Springer, pp. 361\u2013378 (2020)","DOI":"10.1007\/978-3-030-58539-6_22"},{"key":"10481_CR60","doi-asserted-by":"crossref","unstructured":"Pandey, K., Mandt, S.: A complete recipe for diffusion generative models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4261\u20134272 (2023)","DOI":"10.1109\/ICCV51070.2023.00393"},{"key":"10481_CR61","unstructured":"Pang, B., Han, T., Nijkamp, E., et al,: Learning latent space energy-based prior model. Advances in Neural Information Processing Systems 33, pp.21994\u201322008 (2020)"},{"key":"10481_CR62","unstructured":"Papamakarios, G., Nalisnick, E., Rezende, D.J., et\u00a0al: Normalizing flows for probabilistic modeling and inference (2019). arXiv:1912.02762"},{"key":"10481_CR63","doi-asserted-by":"crossref","unstructured":"Papaspiliopoulos, O., Roberts, G.O., Sk\u00f6ld, M.: A general framework for the parametrization of hierarchical models. Statistical Science, pp. 59\u201373 (2007)","DOI":"10.1214\/088342307000000014"},{"key":"10481_CR64","unstructured":"Peis, I., Ma, C., Hern\u00e1ndez-Lobato, J.M.: Missing data imputation and acquisition with deep hierarchical models and Hamiltonian Monte Carlo (2022). arXiv:2202.04599"},{"key":"10481_CR65","unstructured":"Ranganath, R., Tran, D., Blei, D.M.: Hierarchical variational models. In: International Conference on Machine Learning (2016)"},{"key":"10481_CR66","unstructured":"Rezende, D., Mohamed, S.: Variational inference with normalizing flows. In: Proceedings of The 32nd International Conference on Machine Learning, pp. 1530\u20131538 (2015)"},{"key":"10481_CR67","unstructured":"Rezende, D.J., Mohamed, S., Wierstra, D.: Stochastic backpropagation and approximate inference in deep generative models. In: Proceedings of the 31st International Conference on Machine Learning (ICML-14), pp. 1278\u20131286 (2014)"},{"issue":"1","key":"10481_CR68","first-page":"110","volume":"7","author":"G Roberts","year":"1997","unstructured":"Roberts, G., Gelman, A., Gilks, W.: Weak convergence and optimal scaling of random walk metropolis algorithms. Ann. Appl. Probab. 7(1), 110\u2013120 (1997)","journal-title":"Ann. Appl. Probab."},{"key":"10481_CR69","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., et\u00a0al: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"10481_CR70","unstructured":"Rosca, M., Lakshminarayanan, B., Mohamed, S.: Distribution matching in variational inference (2018). arXiv:1802.06847"},{"key":"10481_CR71","unstructured":"Ruiz, F., Titsias, M.: A Contrastive divergence for combining variational inference and MCMC. In: International Conference on Machine Learning, pp. 5537\u20135545 (2019)"},{"key":"10481_CR72","unstructured":"Ruiz, F.J., Titsias, M.K., Cemgil, T., et\u00a0al: Unbiased gradient estimation for variational auto-encoders using coupled Markov chains. In: Uncertainty in Artificial Intelligence, PMLR, pp. 707\u2013717 (2021)"},{"key":"10481_CR73","unstructured":"Salimans, T., Kingma, D.P., Welling, M., et\u00a0al: Markov Chain Monte Carlo and variational inference: bridging the gap. In: ICML, pp. 1218\u20131226 (2015)"},{"key":"10481_CR74","unstructured":"Salimans, T., Karpathy, A., Chen, X., et\u00a0al: Pixelcnn++: improving the pixelcnn with discretized logistic mixture likelihood and other modifications. In: International Conference on Learning Representations (2017)"},{"key":"10481_CR75","unstructured":"Singhal, R., Goldstein, M., Ranganath, R.: Where to diffuse, how to diffuse and how to get back: automated learning in multivariate diffusions. In: International Conference on Learning Representations (2023)"},{"key":"10481_CR76","first-page":"12533","volume":"34","author":"A Sinha","year":"2021","unstructured":"Sinha, A., Song, J., Meng, C., et al.: D2c: diffusion-decoding models for few-shot conditional generation. Adv. Neural. Inf. Process. Syst. 34, 12533\u201312548 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"10481_CR77","unstructured":"Sohl-Dickstein, J., Weiss, E., Maheswaranathan, N., et\u00a0al: Deep unsupervised learning using nonequilibrium thermodynamics. In: International Conference on Machine Learning, PMLR, pp. 2256\u20132265 (2015)"},{"key":"10481_CR78","first-page":"3738","volume":"29","author":"CK S\u00f8nderby","year":"2016","unstructured":"S\u00f8nderby, C.K., Raiko, T., Maal\u00f8e, L., et al.: Ladder variational autoencoders. Adv. Neural. Inf. Process. Syst. 29, 3738\u20133746 (2016)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"10481_CR79","unstructured":"Song, Y., Ermon, S.: Generative modeling by estimating gradients of the data distribution. Advances in Neural Information Processing Systems 32, pp. 11918\u201311930 (2019)"},{"key":"10481_CR80","unstructured":"Song, Y., Sohl-Dickstein, J., Kingma, D.P., et\u00a0al: Score-based generative modeling through stochastic differential equations. In: International Conference on Learning Representations (2020)"},{"key":"10481_CR81","unstructured":"Taniguchi, S., Iwasawa, Y., Kumagai, W., et\u00a0al: Langevin autoencoders for learning deep latent variable models (2022). arXiv:2209.07036"},{"key":"10481_CR82","unstructured":"Thin, A., Kotelevskii, N., Denain, J.S., et\u00a0al: Metflow: a new efficient method for bridging the gap between Markov Chain Monte Carlo and variational inference (2020). arXiv:2002.12253"},{"issue":"3","key":"10481_CR83","doi-asserted-by":"publisher","first-page":"611","DOI":"10.1111\/1467-9868.00196","volume":"61","author":"ME Tipping","year":"1999","unstructured":"Tipping, M.E., Bishop, C.M.: Probabilistic principal component analysis. J. R. Stat. Soc. Ser. B (Stat. Methodol.) 61(3), 611\u2013622 (1999)","journal-title":"J. R. Stat. Soc. Ser. B (Stat. Methodol.)"},{"key":"10481_CR84","unstructured":"Titsias, M., Dellaportas, P.: Gradient-based adaptive Markov chain Monte Carlo. In: Advances in Neural Information Processing Systems, pp. 15704\u201315713 (2019)"},{"key":"10481_CR85","unstructured":"Titsias, M., L\u00e1zaro-Gredilla, M.: Doubly stochastic variational bayes for non-conjugate inference. In: Proceedings of the 31st International Conference on Machine Learning (ICML-14), pp. 1971\u20131979 (2014)"},{"key":"10481_CR86","unstructured":"Titsias MK (2017) Learning model reparametrizations: implicit variational inference by fitting MCMC distributions. arXiv:1708.01529"},{"key":"10481_CR87","unstructured":"Titsias, M.K., Ruiz, F.: Unbiased implicit variational inference. In: The 22nd international conference on artificial intelligence and statistics, pp. 167\u2013176 (2019)"},{"key":"10481_CR88","unstructured":"Tomczak, J.M., Welling, M.: VAE with a VampPrior (2017). arXiv:1705.07120"},{"key":"10481_CR89","unstructured":"Tran, D., Blei, D., Airoldi, E.M.: Copula variational inference. In: Advances in Neural Information Processing Systems, pp. 3564\u20133572 (2015)"},{"key":"10481_CR90","unstructured":"Tran, D., Ranganath, R., Blei, D.M.: Deep and hierarchical implicit models. arXiv:1702.08896 (2017)"},{"key":"10481_CR91","unstructured":"Vahdat, A., Kautz, J.: NVAE: a deep hierarchical variational autoencoder (2020). arXiv:2007.03898"},{"key":"10481_CR92","unstructured":"Vahdat, A., Kreis, K., Kautz, J.: Score-based generative modeling in latent space. Advances in Neural Information Processing Systems 34 (2021)"},{"issue":"7","key":"10481_CR93","doi-asserted-by":"publisher","first-page":"1661","DOI":"10.1162\/NECO_a_00142","volume":"23","author":"P Vincent","year":"2011","unstructured":"Vincent, P.: A connection between score matching and denoising autoencoders. Neural Comput. 23(7), 1661\u20131674 (2011)","journal-title":"Neural Comput."},{"key":"10481_CR94","unstructured":"Wolf, C., Karl, M., van\u00a0der Smagt, P.: Variational inference with Hamiltonian Monte Carlo (2016). arXiv:1609.08203"},{"key":"10481_CR95","first-page":"5933","volume":"33","author":"H Wu","year":"2020","unstructured":"Wu, H., K\u00f6hler, J., No\u00e9, F.: Stochastic normalizing flows. Adv. Neural. Inf. Process. Syst. 33, 5933\u20135944 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"270","key":"10481_CR96","first-page":"1","volume":"23","author":"K Wu","year":"2022","unstructured":"Wu, K., Schmidler, S., Chen, Y.: Minimax mixing time of the metropolis-adjusted Langevin algorithm for log-concave sampling. J. Mach. Learn. Res. 23(270), 1\u201363 (2022)","journal-title":"J. Mach. Learn. Res."},{"key":"10481_CR97","unstructured":"Yin, M., Zhou, M.: Semi-implicit variational inference. In: International Conference on Machine Learning, pp. 5646\u20135655 (2018)"},{"key":"10481_CR98","unstructured":"Yu, L., Xie, T., Zhu, Y., et\u00a0al: Hierarchical semi-implicit variational iference with application to diffusion model acceleration. In: Thirty-Seventh Conference on Neural Information Processing Systems (2023)"}],"container-title":["Statistics and Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11222-024-10481-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11222-024-10481-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11222-024-10481-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,3]],"date-time":"2024-10-03T15:07:40Z","timestamp":1727968060000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11222-024-10481-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,6]]},"references-count":98,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2024,10]]}},"alternative-id":["10481"],"URL":"https:\/\/doi.org\/10.1007\/s11222-024-10481-x","relation":{},"ISSN":["0960-3174","1573-1375"],"issn-type":[{"type":"print","value":"0960-3174"},{"type":"electronic","value":"1573-1375"}],"subject":[],"published":{"date-parts":[[2024,8,6]]},"assertion":[{"value":"24 August 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 July 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 August 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declaration"}},{"value":"The authors declare no Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"164"}}