Sampling from Discrete Energy-Based Models with Quality/Efficiency
Trade-offs
- URL: http://arxiv.org/abs/2112.05702v1
- Date: Fri, 10 Dec 2021 17:51:37 GMT
- Title: Sampling from Discrete Energy-Based Models with Quality/Efficiency
Trade-offs
- Authors: Bryan Eikema, Germ\'an Kruszewski, Hady Elsahar, Marc Dymetman
- Abstract summary: Energy-Based Models (EBMs) allow for extremely flexible specifications of probability distributions.
They do not provide a mechanism for obtaining exact samples from these distributions.
We propose a new approximate sampling technique, Quasi Rejection Sampling (QRS), that allows for a trade-off between sampling efficiency and sampling quality.
- Score: 3.491202838583993
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Energy-Based Models (EBMs) allow for extremely flexible specifications of
probability distributions. However, they do not provide a mechanism for
obtaining exact samples from these distributions. Monte Carlo techniques can
aid us in obtaining samples if some proposal distribution that we can easily
sample from is available. For instance, rejection sampling can provide exact
samples but is often difficult or impossible to apply due to the need to find a
proposal distribution that upper-bounds the target distribution everywhere.
Approximate Markov chain Monte Carlo sampling techniques like
Metropolis-Hastings are usually easier to design, exploiting a local proposal
distribution that performs local edits on an evolving sample. However, these
techniques can be inefficient due to the local nature of the proposal
distribution and do not provide an estimate of the quality of their samples. In
this work, we propose a new approximate sampling technique, Quasi Rejection
Sampling (QRS), that allows for a trade-off between sampling efficiency and
sampling quality, while providing explicit convergence bounds and diagnostics.
QRS capitalizes on the availability of high-quality global proposal
distributions obtained from deep learning models. We demonstrate the
effectiveness of QRS sampling for discrete EBMs over text for the tasks of
controlled text generation with distributional constraints and paraphrase
generation. We show that we can sample from such EBMs with arbitrary precision
at the cost of sampling efficiency.
Related papers
- Iterated Denoising Energy Matching for Sampling from Boltzmann Densities [109.23137009609519]
Iterated Denoising Energy Matching (iDEM)
iDEM alternates between (I) sampling regions of high model density from a diffusion-based sampler and (II) using these samples in our matching objective.
We show that the proposed approach achieves state-of-the-art performance on all metrics and trains $2-5times$ faster.
arXiv Detail & Related papers (2024-02-09T01:11:23Z) - A Block Metropolis-Hastings Sampler for Controllable Energy-based Text
Generation [78.81021361497311]
We develop a novel Metropolis-Hastings (MH) sampler that proposes re-writes of the entire sequence in each step via iterative prompting of a large language model.
Our new sampler allows for more efficient and accurate sampling from a target distribution and (b) allows generation length to be determined through the sampling procedure rather than fixed in advance.
arXiv Detail & Related papers (2023-12-07T18:30:15Z) - Optimal Budgeted Rejection Sampling for Generative Models [54.050498411883495]
Rejection sampling methods have been proposed to improve the performance of discriminator-based generative models.
We first propose an Optimal Budgeted Rejection Sampling scheme that is provably optimal.
Second, we propose an end-to-end method that incorporates the sampling scheme into the training procedure to further enhance the model's overall performance.
arXiv Detail & Related papers (2023-11-01T11:52:41Z) - Conditional Sampling of Variational Autoencoders via Iterated
Approximate Ancestral Sampling [7.357511266926065]
Conditional sampling of variational autoencoders (VAEs) is needed in various applications, such as missing data imputation, but is computationally intractable.
A principled choice forally exact conditional sampling is Metropolis-within-Gibbs (MWG)
arXiv Detail & Related papers (2023-08-17T16:08:18Z) - Entropy-based Training Methods for Scalable Neural Implicit Sampler [15.978655106034113]
Efficiently sampling from un-normalized target distributions is a fundamental problem in scientific computing and machine learning.
In this paper, we propose an efficient and scalable neural implicit sampler that overcomes these limitations.
Our sampler can generate large batches of samples with low computational costs by leveraging a neural transformation that directly maps easily sampled latent vectors to target samples.
arXiv Detail & Related papers (2023-06-08T05:56:05Z) - LSB: Local Self-Balancing MCMC in Discrete Spaces [2.385916960125935]
This work considers using machine learning to adapt the proposal distribution to the target, in order to improve the sampling efficiency in the purely discrete domain.
We call the resulting sampler as the Locally Self-Balancing Sampler (LSB)
arXiv Detail & Related papers (2021-09-08T18:31:26Z) - Reparameterized Sampling for Generative Adversarial Networks [71.30132908130581]
We propose REP-GAN, a novel sampling method that allows general dependent proposals by REizing the Markov chains into the latent space of the generator.
Empirically, extensive experiments on synthetic and real datasets demonstrate that our REP-GAN largely improves the sample efficiency and obtains better sample quality simultaneously.
arXiv Detail & Related papers (2021-07-01T10:34:55Z) - Uncorrelated problem-specific samples of quantum states from zero-mean
Wishart distributions [4.289102530380288]
We present a two-step algorithm for sampling from the quantum state space.
We establish the explicit form of the induced Wishart distribution for quantum states.
We demonstrate that this sampling algorithm is very efficient for one-qubit and two-qubit states, and reasonably efficient for three-qubit states.
arXiv Detail & Related papers (2021-06-16T03:06:41Z) - Exposing the Implicit Energy Networks behind Masked Language Models via
Metropolis--Hastings [57.133639209759615]
We interpret sequences as energy-based sequence models and propose two energy parametrizations derivable from traineds.
We develop a tractable emph scheme based on the Metropolis-Hastings Monte Carlo algorithm.
We validate the effectiveness of the proposed parametrizations by exploring the quality of samples drawn from these energy-based models.
arXiv Detail & Related papers (2021-06-04T22:04:30Z) - Learning Energy-Based Models by Diffusion Recovery Likelihood [61.069760183331745]
We present a diffusion recovery likelihood method to tractably learn and sample from a sequence of energy-based models.
After training, synthesized images can be generated by the sampling process that initializes from Gaussian white noise distribution.
On unconditional CIFAR-10 our method achieves FID 9.58 and inception score 8.30, superior to the majority of GANs.
arXiv Detail & Related papers (2020-12-15T07:09:02Z) - A Neural Network MCMC sampler that maximizes Proposal Entropy [3.4698840925433765]
Augmenting samplers with neural networks can potentially improve their efficiency.
Our network architecture utilizes the gradient of the target distribution for generating proposals.
The adaptive sampler achieves unbiased sampling with significantly higher proposal entropy than Langevin dynamics sampler.
arXiv Detail & Related papers (2020-10-07T18:01:38Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.