English
Related papers

Related papers: Learning to Importance Sample in Primary Sample Sp…

200 papers

The paper introduces AND/OR importance sampling for probabilistic graphical models. In contrast to importance sampling, AND/OR importance sampling caches samples in the AND/OR space and then extracts a new sample mean from the stored…

Artificial Intelligence · Computer Science 2012-06-18 Vibhav Gogate , Rina Dechter

Minibatching is a very well studied and highly popular technique in supervised learning, used by practitioners due to its ability to accelerate training through better utilization of parallel processing power and reduction of stochastic…

Machine Learning · Computer Science 2016-02-09 Dominik Csiba , Peter Richtárik

Generative Adversarial Networks (GAN) training process, in most cases, apply Uniform or Gaussian sampling methods in the latent space, which probably spends most of the computation on examples that can be properly handled and easy to…

Machine Learning · Computer Science 2022-12-19 Shiyu Yi , Donglin Zhan , Wenqing Zhang , Denglin Jiang , Kang An , Hao Wang

The rise of artificial intelligence (AI) hinges on the efficient training of modern deep neural networks (DNNs) for non-convex optimization and uncertainty quantification, which boils down to a non-convex Bayesian learning problem. A…

Computation · Statistics 2023-06-01 Wei Deng

Acceptance-rejection (AR), Independent Metropolis Hastings (IMH) or importance sampling (IS) Monte Carlo (MC) simulation algorithms all involve computing ratios of probability density functions (pdfs). On the other hand, classifiers…

Methodology · Statistics 2023-09-11 Elouan Argouarc'h , François Desbouvries

We introduce a theoretical and practical framework for efficient importance sampling of mini-batch samples for gradient estimation from single and multiple probability distributions. To handle noisy gradients, our framework dynamically…

Machine Learning · Computer Science 2025-01-29 Corentin Salaün , Xingchang Huang , Iliyan Georgiev , Niloy J. Mitra , Gurprit Singh

Most reinforcement learning algorithms take advantage of an experience replay buffer to repeatedly train on samples the agent has observed in the past. Not all samples carry the same amount of significance and simply assigning equal…

Machine Learning · Computer Science 2023-11-02 Shivakanth Sujit , Somjit Nath , Pedro H. M. Braga , Samira Ebrahimi Kahou

Controlled capture of real-world material appearance yields tabulated sets of highly realistic reflectance data. In practice, however, its high memory footprint requires compressing into a representation that can be used efficiently in…

Graphics · Computer Science 2021-05-18 Alejandro Sztrajman , Gilles Rainer , Tobias Ritschel , Tim Weyrich

Learning with few samples is a major challenge for parameter-rich models like deep networks. In contrast, people learn complex new concepts even from very few examples, suggesting that the sample complexity of learning can often be reduced.…

Machine Learning · Computer Science 2019-06-11 Roman Visotsky , Yuval Atzmon , Gal Chechik

Achieving invariance to nuisance transformations is a fundamental challenge in the construction of robust and reliable vision systems. Existing approaches to invariance scale exponentially with the dimension of the family of…

Computer Vision and Pattern Recognition · Computer Science 2022-03-11 Sam Buchanan , Jingkai Yan , Ellie Haber , John Wright

In the context of Monte Carlo sampling for lattice models, the complexity of the energy landscape often leads to Markov chains being trapped in local optima, thereby increasing the correlation between samples and reducing sampling…

Statistical Mechanics · Physics 2024-10-29 Jiewei Ding , Jiahao Su , Ho-Kin Tang , Wing Chi Yu

We introduce neural particle smoothing, a sequential Monte Carlo method for sampling annotations of an input string from a given probability model. In contrast to conventional particle filtering algorithms, we train a proposal distribution…

Computation and Language · Computer Science 2018-05-01 Chu-Cheng Lin , Jason Eisner

This paper proposes a method for hiding the least-important samples during the training of deep neural networks to increase efficiency, i.e., to reduce the cost of training. Using information about the loss and prediction confidence during…

Distributed, Parallel, and Cluster Computing · Computer Science 2023-10-17 Truong Thao Nguyen , Balazs Gerofi , Edgar Josafat Martinez-Noriega , François Trahay , Mohamed Wahib

Sampling-based motion planning methods, while effective in high-dimensional spaces, often suffer from inefficiencies due to irregular sampling distributions, leading to suboptimal exploration of the configuration space. In this paper, we…

Robotics · Computer Science 2025-08-28 Makram Chahine , T. Konstantin Rusch , Zach J. Patterson , Daniela Rus

The output distribution of a neural network (NN) over the entire input space captures the complete input-output mapping relationship, offering insights toward a more comprehensive NN understanding. Exhaustive enumeration or traditional…

Artificial Intelligence · Computer Science 2023-02-22 Weitang Liu , Ying-Wai Li , Yi-Zhuang You , Jingbo Shang

Recently, many neural network-based image compression methods have shown promising results superior to the existing tool-based conventional codecs. However, most of them are often trained as separate models for different target bit rates,…

Image and Video Processing · Electrical Eng. & Systems 2022-11-09 Jooyoung Lee , Seyoon Jeong , Munchurl Kim

Quality by design in pharmaceutical manufacturing hinges on computational methods and tools that are capable of accurate quantitative prediction of the design space. This paper investigates Bayesian approaches to design space…

The use of sparse precision (inverse covariance) matrices has become popular because they allow for efficient algorithms for joint inference in high-dimensional models. Many applications require the computation of certain elements of the…

Computation · Statistics 2017-12-06 Per Sidén , Finn Lindgren , David Bolin , Mattias Villani

We propose an adaptive importance sampling scheme for Gaussian approximations of intractable posteriors. Optimization-based approximations like variational inference can be too inaccurate while existing Monte Carlo methods can be too slow.…

Computation · Statistics 2025-02-04 Willem van den Boom , Andrea Cremaschi , Alexandre H. Thiery

Random geometric graphs defined on Euclidean subspaces, also called Gilbert graphs, are widely used to model spatially embedded networks across various domains. In such graphs, nodes are located at random in Euclidean space, and any two…

Probability · Mathematics 2026-04-23 Sarat Moka , Christian Hirsch , Volker Schmidt , Dirk Kroese