اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدPosterior-Aided Regularization for Likelihood-Free Inference
68
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
The recent development of likelihood-free inference aims training a flexible density estimator for the target posterior with a set of input-output pairs from simulation. Given the diversity of simulation structures, it is difficult to find a single unified inference method for each simulation model. This paper proposes a universally applicable regularization technique, called Posterior-Aided Regularization (PAR), which is applicable to learning the density estimator, regardless of the model structure. Particularly, PAR solves the mode collapse problem that arises as the output dimension of the simulation increases. PAR resolves this posterior mode degeneracy through a mixture of 1) the reverse KL divergence with the mode seeking property; and 2) the mutual information for the high quality representation on likelihood. Because of the estimation intractability of PAR, we provide a unified estimation method of PAR to estimate both reverse KL term and mutual information term with a single neural network. Afterwards, we theoretically prove the asymptotic convergence of the regularized optimal solution to the unregularized optimal solution as the regularization magnitude converges to zero. Additionally, we empirically show that past sequential neural likelihood inferences in conjunction with PAR present the statistically significant gains on diverse simulation tasks.
قيم البحث
اقرأ أيضاً
Generative Adversarial Network (GAN) can be viewed as an implicit estimator of a data distribution, and this perspective motivates using the adversarial concept in the true input parameter estimation of black-box generators. While previous works on l
ikelihood-free inference introduces an implicit proposal distribution on the generator input, this paper analyzes theoretic limitations of the proposal distribution approach. On top of that, we introduce a new algorithm, Adversarial Likelihood-Free Inference (ALFI), to mitigate the analyzed limitations, so ALFI is able to find the posterior distribution on the input parameter for black-box generative models. We experimented ALFI with diverse simulation models as well as pre-trained statistical models, and we identified that ALFI achieves the best parameter estimation accuracy with a limited simulation budget.
Bayesian inference without the access of likelihood, or likelihood-free inference, has been a key research topic in simulations, to yield a more realistic generation result. Recent likelihood-free inference updates an approximate posterior sequential
ly with the dataset of the cumulative simulation input-output pairs over inference rounds. Therefore, the dataset is gathered through the iterative simulations with sampled inputs from a proposal distribution by MCMC, which becomes the key of inference quality in this sequential framework. This paper introduces a new proposal modeling, named as Implicit Surrogate Proposal (ISP), to generate a cumulated dataset with further sample efficiency. ISP constructs the cumulative dataset in the most diverse way by drawing i.i.d samples via a feed-forward fashion, so the posterior inference does not suffer from the disadvantages of MCMC caused by its non-i.i.d nature, such as auto-correlation and slow mixing. We analyze the convergence property of ISP in both theoretical and empirical aspects to guarantee that ISP provides an asymptotically exact sampler. We demonstrate that ISP outperforms the baseline inference algorithms on simulations with multi-modal posteriors.
Fast and automated inference of binary-lens, single-source (2L1S) microlensing events with sampling-based Bayesian algorithms (e.g., Markov Chain Monte Carlo; MCMC) is challenged on two fronts: high computational cost of likelihood evaluations with m
icrolensing simulation codes, and a pathological parameter space where the negative-log-likelihood surface can contain a multitude of local minima that are narrow and deep. Analysis of 2L1S events usually involves grid searches over some parameters to locate approximate solutions as a prerequisite to posterior sampling, an expensive process that often requires human-in-the-loop domain expertise. As the next-generation, space-based microlensing survey with the Roman Space Telescope is expected to yield thousands of binary microlensing events, a new fast and automated method is desirable. Here, we present a likelihood-free inference (LFI) approach named amortized neural posterior estimation, where a neural density estimator (NDE) learns a surrogate posterior $hat{p}(theta|x)$ as an observation-parametrized conditional probability distribution, from pre-computed simulations over the full prior space. Trained on 291,012 simulated Roman-like 2L1S simulations, the NDE produces accurate and precise posteriors within seconds for any observation within the prior support without requiring a domain expert in the loop, thus allowing for real-time and automated inference. We show that the NDE also captures expected posterior degeneracies. The NDE posterior could then be refined into the exact posterior with a downstream MCMC sampler with minimal burn-in steps.
A multi-layer deep Gaussian process (DGP) model is a hierarchical composition of GP models with a greater expressive power. Exact DGP inference is intractable, which has motivated the recent development of deterministic and stochastic approximation m
ethods. Unfortunately, the deterministic approximation methods yield a biased posterior belief while the stochastic one is computationally costly. This paper presents an implicit posterior variational inference (IPVI) framework for DGPs that can ideally recover an unbiased posterior belief and still preserve time efficiency. Inspired by generative adversarial networks, our IPVI framework achieves this by casting the DGP inference problem as a two-player game in which a Nash equilibrium, interestingly, coincides with an unbiased posterior belief. This consequently inspires us to devise a best-response dynamics algorithm to search for a Nash equilibrium (i.e., an unbiased posterior belief). Empirical evaluation shows that IPVI outperforms the state-of-the-art approximation methods for DGPs.
The variational autoencoder (VAE) is a popular model for density estimation and representation learning. Canonically, the variational principle suggests to prefer an expressive inference model so that the variational approximation is accurate. Howeve
r, it is often overlooked that an overly-expressive inference model can be detrimental to the test set performance of both the amortized posterior approximator and, more importantly, the generative density estimator. In this paper, we leverage the fact that VAEs rely on amortized inference and propose techniques for amortized inference regularization (AIR) that control the smoothness of the inference model. We demonstrate that, by applying AIR, it is possible to improve VAE generalization on both inference and generative performance. Our paper challenges the belief that amortized inference is simply a mechanism for approximating maximum likelihood training and illustrates that regularization of the amortization family provides a new direction for understanding and improving generalization in VAEs.
الأسئلة المقترحة
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
