On Importance Sampling-Based Evaluation of Latent Language Models
Language models that use additional latent structures (e.g., syntax trees, coreference chains, knowledge graph links) provide several advantages over traditional language models. However, likelihood-based evaluation of these models is often intractable as it requires marginalizing over the latent space. Existing works avoid this issue by using importance sampling. Although this approach has asymptotic guarantees, analysis is rarely conducted on the effect of decisions such as sample size and choice of proposal distribution on the reported estimates. In this paper, we carry out this analysis for three models: RNNG, EntityNLM, and KGLM. In addition, we elucidate subtle differences in how importance sampling is applied in these works that can have substantial effects on the final estimates, as well as provide theoretical results which reinforce the validity of this technique.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
FIS-GAN: GAN with Flow-based Importance Sampling
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 handle…
Density EstimationStochastic OptimizationEnhanced Importance Sampling through Latent Space Exploration in Normalizing Flows
Importance sampling is a rare event simulation technique used in Monte Carlo simulations to bias the sampling distribution towards the rare event of interest. By assigning appropriate weights to sampled points, importanc…
Autonomous RacingCollision AvoidanceProposal-Guided Greedy Surrogate Refinement for PDE-Driven High-Dimensional Rare-Event Estimation
Accurate surrogate construction for PDE-driven high-dimensional rare-event simulation is challenging when performance evaluations are expensive. Since a globally accurate surrogate may require many high-fidelity evaluati…
Manifold Bandits: Bayesian Curriculum Learning over the Latent Geometry of Large Language Models
Reinforcement learning (RL) is a central approach for improving reasoning capabilities in large language models (LLMs), where training efficiency depends critically on how problems are sampled during optimization. Existi…
Reinforcement LearningTraining Variational Auto Encoders with Discrete Latent Representations using Importance Sampling
The Variational Auto Encoder (VAE) is a popular generative latent variable model that is often applied for representation learning. Standard VAEs assume continuous valued latent variables and are trained by maximizati…
Representation Learning