paper-with-me

홈 › Papers

Guiding Time-Varying Generative Models with Natural Gradients on Exponential Family Manifold

2025-02-11 · Song Liu, Leyang Wang, Yakun Wang

Optimising probabilistic models is a well-studied field in statistics. However, its connection with the training of generative models remains largely under-explored. In this paper, we show that the evolution of time-varying generative models can be projected onto an exponential family manifold, naturally creating a link between the parameters of a generative model and those of a probabilistic model. We then train the generative model by moving its projection on the manifold according to the natural gradient descent scheme. This approach also allows us to approximate the natural gradient of the KL divergence efficiently without relying on MCMC for intractable models. Furthermore, we propose particle versions of the algorithm, which feature closed-form update rules for any parametric model within the exponential family. Through toy and real-world experiments, we validate the effectiveness of the proposed algorithms.

📄 PDF Abstract BibTeX arXiv:2502.07650

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Natural Gradient Descent 설명 없음

Similar Papers 제목 키워드 기반

Personalizing Text-to-Image Generation via Aesthetic Gradients

2022-09-25 · Victor Gallego

This work proposes aesthetic gradients, a method to personalize a CLIP-conditioned diffusion model by guiding the generative process towards custom aesthetics defined by the user from a set of images. The approach is val…

Image GenerationText to Image GenerationText-to-Image Generation

Generative Guiding Block: Synthesizing Realistic Looking Variants Capable of Even Large Change Demands

2019-07-02 · Minho Park, Hak Gu Kim, Yong Man Ro

Realistic image synthesis is to generate an image that is perceptually indistinguishable from an actual image. Generating realistic looking images with large variations (e.g., large spatial deformations and large pose ch…

Image Generation

T-GMP: Terrain-conditioned Generative Motion Priors for Versatile and Natural Humanoid Locomotion

2026-06-05 · Junhong Guo, Hao Hu, Chen Chen, Haoxuan Han 외 arxiv

Achieving both anthropomorphic naturalness and robust terrain traversal remains a fundamental challenge in humanoid locomotion. Existing Reinforcement Learning (RL) approaches typically rely on fixed motion priors, limit…

Reinforcement Learning

ReSplat: Learning Recurrent Gaussian Splatting

2025-10-09 · Haofei Xu, Daniel Barath, Andreas Geiger, Marc Pollefeys arxiv

While existing feed-forward Gaussian splatting models offer computational efficiency and can generalize to sparse view settings, their performance is fundamentally constrained by relying on a single forward pass for infe…

Computational Efficiency

Guiding Representation Learning in Deep Generative Models with Policy Gradients

2021-01-01 · Luca Lach, Timo Korthals, Malte Schilling, Helge Ritter

Variational Auto Encoder (VAE) provide an efficient latent space representation of complex data distributions which is learned in an unsupervised fashion. Using such a representation as input to Reinforcement Learning (R…

Reinforcement Learning (RL)Representation Learning