Sampling from Discrete Energy-Based Models with Quality/Efficiency Trade-offs
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Paraphrase GenerationText GenerationSimilar Papers 제목 키워드 기반
Discrete-state Continuous-time Diffusion for Graph Generation
Graph is a prevalent discrete data structure, whose generation has wide applications such as drug discovery and circuit design. Diffusion generative models, as an emerging research focus, have been applied to graph gener…
Drug DiscoveryGraph GenerationAssessing generative modeling approaches for free energy estimates in condensed matter
The accurate estimation of free energy differences between two states is a long-standing challenge in molecular simulations. Traditional approaches generally rely on sampling multiple intermediate states to ensure suffic…
On the Error-Correcting Effects of Stochasticity in Discrete Diffusion
Discrete diffusion models achieve strong performance in text and image generation, but their inference remains slow and must inherently balance sampling efficiency and sample quality. In this work, we present a systemati…
Image GenerationExploring Non-Convex Discrete Energy Landscapes: An Efficient Langevin-Like Sampler with Replica Exchange
Gradient-based Discrete Samplers (GDSs) are effective for sampling discrete energy landscapes. However, they often stagnate in complex, non-convex settings. To improve exploration, we introduce the Discrete Replica EXcha…
Age-of-information minimization via opportunistic sampling by an energy harvesting source
Herein, minimization of time-averaged age-of-information (AoI) in an energy harvesting (EH) source setting is considered. The EH source opportunistically samples one or multiple processes over discrete time instants and …
Q-Learning