paper-with-me

Papers

Exploring bidirectional bounds for minimax-training of Energy-based models

2025-06-05 · Cong Geng, Jia Wang, Li Chen, Zhiyong Gao, Jes Frellsen, Søren Hauberg

Energy-based models (EBMs) estimate unnormalized densities in an elegant framework, but they are generally difficult to train. Recent work has linked EBMs to generative adversarial networks, by noting that they can be trained through a minimax game using a variational lower bound. To avoid the instabilities caused by minimizing a lower bound, we propose to instead work with bidirectional bounds, meaning that we maximize a lower bound and minimize an upper bound when training the EBM. We investigate four different bounds on the log-likelihood derived from different perspectives. We derive lower bounds based on the singular values of the generator Jacobian and on mutual information. To upper bound the negative log-likelihood, we consider a gradient penalty-like bound, as well as one based on diffusion processes. In all cases, we provide algorithms for evaluating the bounds. We compare the different bounds to investigate, the pros and cons of the different approaches. Finally, we demonstrate that the use of bidirectional bounds stabilizes EBM training and yields high-quality density estimation and sample generation.

📄 PDF Abstract BibTeX arXiv:2506.04609

Code (0)

등록된 구현이 없습니다.

Tasks

Density Estimation

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…
EBM 설명 없음

Similar Papers 제목 키워드 기반

Bounds all around: training energy-based models with bidirectional bounds

2021-11-01 · NeurIPS 2021 12 · Cong Geng, Jia Wang, Zhiyong Gao, Jes Frellsen 외

Energy-based models (EBMs) provide an elegant framework for density estimation, but they are notoriously difficult to train. Recent work has established links to generative adversarial networks, where the EBM is trained …

AllDensity Estimation

Information-Theoretic Minimax Regret Bounds for Reinforcement Learning based on Duality

2024-10-21 · Raghav Bongole, Amaury Gouverneur, Borja Rodríguez-Gálvez, Tobias J. Oechtering 외

We study agents acting in an unknown environment where the agent's goal is to find a robust policy. We consider robust policies as policies that achieve high cumulative rewards for all possible environments. To this end,…

A Minimax Lower Bound for Low-Rank Matrix-Variate Logistic Regression

2021-05-31 · Batoul Taki, Mohsen Ghassemi, Anand D. Sarwate, Waheed U. Bajwa

This paper considers the problem of matrix-variate logistic regression. It derives the fundamental error threshold on estimating low-rank coefficient matrices in the logistic regression problem by obtaining a lower bound…

regression

Risk level dependent Minimax Quantile lower bounds for Interactive Statistical Decision Making

2025-10-07 · Raghav Bongole, Amirreza Zamani, Tobias J. Oechtering, Mikael Skoglund arxiv

Minimax risk and regret focus on expectation, missing rare failures critical in safety-critical bandits and reinforcement learning. Minimax quantiles capture these tails. Three strands of prior work motivate this study: …

Reinforcement LearningDecision Making

Towards Sharper Risk Bounds for Minimax Problems

2024-10-11 · Bowei Zhu, Shaojie Li, Yong liu

Minimax problems have achieved success in machine learning such as adversarial training, robust optimization, reinforcement learning. For theoretical analysis, current optimal excess risk bounds, which are composed by ge…

Generalization Bounds