Representation learning with efficient extreme learning machine auto-encoders

Zhang, Guanghao

doi:10.32657/10356/146297

Cited by 3 publications

(7 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A popular approach addressing this problem is AIS, an approach pioneered by Crooks [ 24 ] and Neal [ 25 ] based on early work by Jarzynski [ 26 ]. Despite having been introduced over 20 years ago, this approach remains one of the ‘gold standard’ techniques to estimate the evidence unbiasedly and can thus be used to define an ELBO [ 27 , 28 ]. However, as detailed below, it is difficult to obtain low-variance gradient estimators of this ELBO so a generalized version of the AIS estimate based on SIS [ 29 , 30 ] has been instead favoured [ 14 – 16 , 31 , 33 ].…”

Section: Annealed and Sequential Importance Samplingmentioning

confidence: 99%

“…Metropolis–Hastings kernels admit an atomic component. We refer the reader to Thin et al [ 27 ] for a rigorous presentation.…”

Section: Annealed and Sequential Importance Samplingmentioning

confidence: 99%

“…Finally, we present here for simplicity our results for distributions admitting densities w.r.t. the Lebesgue measure, but the reasoning in itself does not depend on this assumption, see [ 16 , 27 ] for a more general presentation.…”

Section: Annealed and Sequential Importance Samplingmentioning

confidence: 99%

“…It follows that the gradient of this ELBO w.r.t.

is given by

where

The first term

can typically be estimated with low variance but the second term

has a higher variance estimate due to the gradient estimate for the accept/reject discrete random variables

[ 35 ], see [ 27 ] for a further discussion. In [ 28 ], the second term is neglected, which introduces a bias that is difficult to quantify.…”

Section: Annealed and Sequential Importance Samplingmentioning

confidence: 99%

See 3 more Smart Citations

Differentiable samplers for deep latent variable models

Doucet

Moulines

Thin

2023

Phil. Trans. R. Soc. A.

View full text Add to dashboard Cite

Latent variable models are a popular class of models in statistics. Combined with neural networks to improve their expressivity, the resulting deep latent variable models have also found numerous applications in machine learning. A drawback of these models is that their likelihood function is intractable so approximations have to be carried out to perform inference. A standard approach consists of maximizing instead an evidence lower bound (ELBO) obtained based on a variational approximation of the posterior distribution of the latent variables. The standard ELBO can, however, be a very loose bound if the variational family is not rich enough. A generic strategy to tighten such bounds is to rely on an unbiased low-variance Monte Carlo estimate of the evidence. We review here some recent importance sampling, Markov chain Monte Carlo and sequential Monte Carlo strategies that have been proposed to achieve this. This article is part of the theme issue ‘Bayesian inference: challenges, perspectives, and prospects’.

show abstract

Section: Annealed and Sequential Importance Samplingmentioning

confidence: 99%

“…Metropolis–Hastings kernels admit an atomic component. We refer the reader to Thin et al [ 27 ] for a rigorous presentation.…”

Section: Annealed and Sequential Importance Samplingmentioning

confidence: 99%

Section: Annealed and Sequential Importance Samplingmentioning

confidence: 99%

“…It follows that the gradient of this ELBO w.r.t.

is given by

where

The first term

can typically be estimated with low variance but the second term

has a higher variance estimate due to the gradient estimate for the accept/reject discrete random variables

[ 35 ], see [ 27 ] for a further discussion. In [ 28 ], the second term is neglected, which introduces a bias that is difficult to quantify.…”

Section: Annealed and Sequential Importance Samplingmentioning

confidence: 99%

See 2 more Smart Citations

Differentiable samplers for deep latent variable models

Doucet

Moulines

Thin

2023

Phil. Trans. R. Soc. A.

View full text Add to dashboard Cite

show abstract

“…Finally, we demonstrate our approach on a rich observation combination lock MDP where it has a latent structure with the observations being high-dimensional and continuous [Misra et al, 2020, Agarwal et al, 2020a, Zhang et al, 2022. We consider the setting where the reward comes from complicated multi-dimensional continuous distributions (thus existing algorithms such as quantile-regression TD [Dabney et al, 2018] do not directly apply here).…”

Section: Introductionmentioning

confidence: 99%

Distributional Offline Policy Evaluation with Predictive Error Guarantees

Wu¹,

Uehara²,

Sun³

2023

Preprint

View full text Add to dashboard Cite

We study the problem of estimating the distribution of the return of a policy using an offline dataset that is not generated from the policy, i.e., distributional offline policy evaluation (OPE). We propose an algorithm called Fitted Likelihood Estimation (FLE), which conducts a sequence of Maximum Likelihood Estimation (MLE) problems and has the flexibility of integrating any state-of-art probabilistic generative models as long as it can be trained via MLE. FLE can be used for both finite horizon and infinite horizon discounted settings where rewards can be multi-dimensional vectors. In our theoretical results, we show that for both finite and infinite horizon discounted settings, FLE can learn distributions that are close to the ground truth under total variation distance and Wasserstein distance, respectively. Our theoretical results hold under the conditions that the offline data covers the test policy's traces and the supervised learning MLE procedures succeed. Experimentally, we demonstrate the performance of FLE with two generative models, Gaussian mixture models and diffusion models. For the multi-dimensional reward setting, FLE with diffusion models is capable of estimating the complicated distribution of the return of a test policy.

show abstract