Timezone: »
This paper considers a new family of variational distributions motivated by Sklar's theorem. This family is based on new copula-like densities on the hypercube with non-uniform marginals which can be sampled efficiently, i.e. with a complexity linear in the dimension d of the state space. Then, the proposed variational densities that we suggest can be seen as arising from these copula-like densities used as base distributions on the hypercube with Gaussian quantile functions and sparse rotation matrices as normalizing flows. The latter correspond to a rotation of the marginals with complexity O(d log d). We provide some empirical evidence that such a variational family can also approximate non-Gaussian posteriors and can be beneficial compared to Gaussian approximations. Our method performs largely comparably to state-of-the-art variational approximations on standard regression and classification benchmarks for Bayesian Neural Networks.
Author Information
Marcel Hirt (University College London)
Petros Dellaportas (University College London, Athens University of Economics and Alan Turing Institute)
Alain Durmus (ENS Paris Saclay)
More from the Same Authors
-
2022 Poster: Local-Global MCMC kernels: the best of both worlds »
Sergey Samsonov · Evgeny Lagutin · Marylou Gabrié · Alain Durmus · Alexey Naumov · Eric Moulines -
2022 Poster: FedPop: A Bayesian Approach for Personalised Federated Learning »
Nikita Kotelevskii · Maxime Vono · Alain Durmus · Eric Moulines -
2021 Poster: NEO: Non Equilibrium Sampling on the Orbits of a Deterministic Transform »
Achille Thin · Yazid Janati El Idrissi · Sylvain Le Corff · Charles Ollion · Eric Moulines · Arnaud Doucet · Alain Durmus · Christian X Robert -
2021 Poster: Entropy-based adaptive Hamiltonian Monte Carlo »
Marcel Hirt · Michalis Titsias · Petros Dellaportas -
2021 Poster: Fast Approximation of the Sliced-Wasserstein Distance Using Concentration of Random Projections »
Kimia Nadjahi · Alain Durmus · Pierre E Jacob · Roland Badeau · Umut Simsekli -
2021 Poster: Tight High Probability Bounds for Linear Stochastic Approximation with Fixed Stepsize »
Alain Durmus · Eric Moulines · Alexey Naumov · Sergey Samsonov · Kevin Scaman · Hoi-To Wai -
2020 Poster: Statistical and Topological Properties of Sliced Probability Divergences »
Kimia Nadjahi · Alain Durmus · Lénaïc Chizat · Soheil Kolouri · Shahin Shahrampour · Umut Simsekli -
2020 Spotlight: Statistical and Topological Properties of Sliced Probability Divergences »
Kimia Nadjahi · Alain Durmus · Lénaïc Chizat · Soheil Kolouri · Shahin Shahrampour · Umut Simsekli -
2020 Poster: Quantitative Propagation of Chaos for SGD in Wide Neural Networks »
Valentin De Bortoli · Alain Durmus · Xavier Fontaine · Umut Simsekli -
2019 Poster: Asymptotic Guarantees for Learning Generative Models with the Sliced-Wasserstein Distance »
Kimia Nadjahi · Alain Durmus · Umut Simsekli · Roland Badeau -
2019 Spotlight: Asymptotic Guarantees for Learning Generative Models with the Sliced-Wasserstein Distance »
Kimia Nadjahi · Alain Durmus · Umut Simsekli · Roland Badeau -
2019 Poster: Gradient-based Adaptive Markov Chain Monte Carlo »
Michalis Titsias · Petros Dellaportas -
2018 Poster: The promises and pitfalls of Stochastic Gradient Langevin Dynamics »
Nicolas Brosse · Alain Durmus · Eric Moulines