paper-with-me

Papers

Black-box $α$-divergence Minimization

2015-11-10 · José Miguel Hernández-Lobato, Yingzhen Li, Mark Rowland, Daniel Hernández-Lobato, Thang Bui, Richard E. Turner

Black-box alpha (BB-$\alpha$) is a new approximate inference method based on the minimization of $\alpha$-divergences. BB-$\alpha$ scales to large datasets because it can be implemented using stochastic gradient descent. BB-$\alpha$ can be applied to complex probabilistic models with little effort since it only requires as input the likelihood function and its gradients. These gradients can be easily obtained using automatic differentiation. By changing the divergence parameter $\alpha$, the method is able to interpolate between variational Bayes (VB) ($\alpha \rightarrow 0$) and an algorithm similar to expectation propagation (EP) ($\alpha = 1$). Experiments on probit regression and neural network regression and classification problems show that BB-$\alpha$ with non-standard settings of $\alpha$, such as $\alpha = 0.5$, usually produces better predictions than with $\alpha \rightarrow 0$ (VB) or $\alpha = 1$ (EP).

📄 PDF Abstract BibTeX arXiv:1511.03243

Code (3)

SuperKam91/bnn tf
tensorflow/models tf
tensorflow/models/tree/master/research/deep_contextual_bandits tf

Tasks

General Classificationregression

Similar Papers 제목 키워드 기반

Equivalence of the Empirical Risk Minimization to Regularization on the Family of f-Divergences

2024-02-01 · Francisco Daunas, Iñaki Esnaola, Samir M. Perlaza, H. Vincent Poor

The solution to empirical risk minimization with $f$-divergence regularization (ERM-$f$DR) is presented under mild conditions on $f$. Under such conditions, the optimal measure is shown to be unique. Examples of the solu…

Inductive Bias

Many Paths to Equilibrium: GANs Do Not Need to Decrease a Divergence At Every Step

2017-10-23 · ICLR 2018 1 · William Fedus, Mihaela Rosca, Balaji Lakshminarayanan, Andrew M. Dai 외

Generative adversarial networks (GANs) are a family of generative models that do not minimize a single training criterion. Unlike other generative models, the data distribution is learned via a game between a generator (…

Empirical Evaluation of Biased Methods for Alpha Divergence Minimization

2021-05-13 · pproximateinference AABI Symposium 2021 1 · Tomas Geffner, Justin Domke

In this paper we empirically evaluate biased methods for alpha-divergence minimization. In particular, we focus on how the bias affects the final solutions found, and how this depends on the dimensionality of the problem…

Non-saturating GAN training as divergence minimization

2020-10-15 · Matt Shannon, Ben Poole, Soroosh Mariooryad, Tom Bagby 외

Non-saturating generative adversarial network (GAN) training is widely used and has continued to obtain groundbreaking results. However so far this approach has lacked strong theoretical justification, in contrast to alt…

DiversityGenerative Adversarial Network

Reparameterized Variational Divergence Minimization for Stable Imitation

2020-06-18 · Dilip Arumugam, Debadeepta Dey, Alekh Agarwal, Asli Celikyilmaz 외

While recent state-of-the-art results for adversarial imitation-learning algorithms are encouraging, recent works exploring the imitation learning from observation (ILO) setting, where trajectories \textit{only} contain …

continuous-controlContinuous ControlImitation Learning