paper-with-me

Papers

Variational Inference Optimized Using the Curved Geometry of Coupled Free Energy

2025-06-10 · Kenric Nelson, Igor Oliveira, Amenah Al-Najafi, Fode Zhang, Hon Keung Tony Ng

We introduce an optimization framework for variational inference based on the coupled free energy, extending variational inference techniques to account for the curved geometry of the coupled exponential family. This family includes important heavy-tailed distributions such as the generalized Pareto and the Student's t. By leveraging the coupled free energy, which is equal to the coupled evidence lower bound (ELBO) of the inverted probabilities, we improve the accuracy and robustness of the learned model. The coupled generalization of Fisher Information metric and the affine connection. The method is applied to the design of a coupled variational autoencoder (CVAE). By using the coupling for both the distributions and cost functions, the reconstruction metric is derived to still be the mean-square average loss with modified constants. The novelty comes from sampling the heavy-tailed latent distribution with its associated coupled probability, which has faster decaying tails. The result is the ability to train a model robust against severe outliers, while assuring that the training process is stable. The Wasserstein-2 or Fr\'echet Inception Distance of the reconstructed CelebA images shows the CVAE has a 3\% improvement over the VAE after 5 epochs of training.

📄 PDF Abstract BibTeX arXiv:2506.09091

Code (0)

등록된 구현이 없습니다.

Tasks

Variational Inference

Methods 이 논문이 사용한 방법론

cVAE 설명 없음
Variational Inference 설명 없음

Similar Papers 제목 키워드 기반

Curved Inference: Concern-Sensitive Geometry in Large Language Model Residual Streams

2025-07-08 · Rob Manson arxiv

We propose Curved Inference - a geometric Interpretability framework that tracks how the residual stream trajectory of a large language model bends in response to shifts in semantic concern. Across 20 matched prompts spa…

Fast Variational Inference in the Conjugate Exponential Family

2012-12-01 · NeurIPS 2012 12 · James Hensman, Magnus Rattray, Neil D. Lawrence

We present a general method for deriving collapsed variational inference algorithms for probabilistic models in the conjugate exponential family. Our method unifies many existing approaches to collapsed variational infer…

Variational Inference

Curved Geometric Networks for Visual Anomaly Recognition

2022-08-02 · Jie Hong, Pengfei Fang, Weihao Li, Junlin Han 외

Learning a latent embedding to understand the underlying nature of data distribution is often formulated in Euclidean spaces with zero curvature. However, the success of the geometry constraints, posed in the embedding s…

Anomaly DetectionAnomaly SegmentationOut of Distribution (OOD) DetectionSegmentation

Geometry Interaction Knowledge Graph Embeddings

2022-06-24 · Zongsheng Cao, Qianqian Xu, Zhiyong Yang, Xiaochun Cao 외

Knowledge graph (KG) embeddings have shown great power in learning representations of entities and relations for link prediction tasks. Previous work usually embeds KGs into a single geometric space such as Euclidean spa…

Knowledge Graph CompletionKnowledge Graph EmbeddingsLink Prediction

Mixed-curvature Variational Autoencoders

2019-11-19 · ICLR 2020 1 · Ondrej Skopek, Octavian-Eugen Ganea, Gary Bécigneul

Euclidean geometry has historically been the typical "workhorse" for machine learning applications due to its power and simplicity. However, it has recently been shown that geometric spaces with constant non-zero curvatu…