paper-with-me

홈 › Papers

Energy-Inspired Models: Learning with Sampler-Induced Distributions

2019-10-31 · NeurIPS 2019 12 · Dieterich Lawson, George Tucker, Bo Dai, Rajesh Ranganath

Energy-based models (EBMs) are powerful probabilistic models, but suffer from intractable sampling and density evaluation due to the partition function. As a result, inference in EBMs relies on approximate sampling algorithms, leading to a mismatch between the model and inference. Motivated by this, we consider the sampler-induced distribution as the model of interest and maximize the likelihood of this model. This yields a class of energy-inspired models (EIMs) that incorporate learned energy functions while still providing exact samples and tractable log-likelihood lower bounds. We describe and evaluate three instantiations of such models based on truncated rejection sampling, self-normalized importance sampling, and Hamiltonian importance sampling. These models outperform or perform comparably to the recently proposed Learned Accept/Reject Sampling algorithm and provide new insights on ranking Noise Contrastive Estimation and Contrastive Predictive Coding. Moreover, EIMs allow us to generalize a recent connection between multi-sample variational lower bounds and auxiliary variable variational inference. We show how recent variational bounds can be unified with EIMs as the variational family.

📄 PDF Abstract BibTeX arXiv:1910.14265

Code (1)

google-research/google-research/tree/master/eim 공식 구현 jax

Tasks

Variational Inference

Methods 이 논문이 사용한 방법론

InfoNCE 설명 없음
Contrastive Predictive Coding Contrastive Predictive Coding (CPC) learns self-supervised representations by predicting the future in latent space by using powerful autoregressive models. The model uses a…

Similar Papers 제목 키워드 기반

On scalable and efficient training of diffusion samplers

2025-05-26 · Minkyu Kim, Kiyoung Seong, Dongyeop Woo, Sungsoo Ahn 외

We address the challenge of training diffusion models to sample from unnormalized energy distributions in the absence of data, the so-called diffusion samplers. Although these approaches have shown promise, they struggle…

MetaDNS: Enhancing Exploration in Discrete Neural Samplers via Well-Tempered Metadynamics

2026-05-20 · Xiaochen Du, Juno Nam, Jaemoo Choi, Wei Guo 외 arxiv

Sampling from discrete distributions with multiple modes and energy barriers is fundamental to machine learning and computational physics. Recent discrete neural samplers like MDNS suffer from mode collapse and fail to s…

One-Step Sampler for Boltzmann Distributions via Drifting

2026-03-18 · Wenhan Cao, Keyu Yan, Lin Zhao arxiv

We present a drifting-based framework for amortized sampling of Boltzmann distributions defined by energy functions. The method trains a one-step neural generator by projecting samples along a Gaussian-smoothed score fie…

Diffusion Path Samplers via Sequential Monte Carlo

2026-01-29 · James Matthew Young, Paula Cordero-Encinar, Sebastian Reich, Andrew Duncan 외 arxiv

We develop diffusion-based samplers for target distributions known up to a normalising constant. To this end, we rely on the well-known diffusion path that smoothly interpolates between a simple base distribution and the…

Oops I Took A Gradient: Scalable Sampling for Discrete Distributions

2021-02-08 · Will Grathwohl, Kevin Swersky, Milad Hashemi, David Duvenaud 외

We propose a general and scalable approximate sampling strategy for probabilistic models with discrete variables. Our approach uses gradients of the likelihood function with respect to its discrete inputs to propose upda…