paper-with-me

Papers

Sequential Function-Space Variational Inference via Gaussian Mixture Approximation

2025-03-10 · Menghao Waiyan William Zhu, Pengcheng Hao, Ercan Engin Kuruoğlu

Continual learning is learning from a sequence of tasks with the aim of learning new tasks without forgetting old tasks. Sequential function-space variational inference (SFSVI) is a continual learning method based on variational inference which uses a Gaussian variational distribution to approximate the distribution of the outputs of a finite number of selected inducing points. Since the posterior distribution of a neural network is multi-modal, a Gaussian distribution could only match one mode of the posterior distribution, and a Gaussian mixture distribution could be used to better approximate the posterior distribution. We propose an SFSVI method which uses a Gaussian mixture variational distribution. We also compare different types of variational inference methods with and without a fixed pre-trained feature extractor. We find that in terms of final average accuracy, Gaussian mixture methods perform better than Gaussian methods and likelihood-focused methods perform better than prior-focused methods.

📄 PDF Abstract BibTeX arXiv:2503.07114

Code (1)

blackblitz/bcl 공식 구현 jax

Tasks

Continual LearningVariational Inference

Methods 이 논문이 사용한 방법론

Variational Inference 설명 없음

Similar Papers 제목 키워드 기반

Generalized Variational Inference in Function Spaces: Gaussian Measures meet Bayesian Deep Learning

2022-05-12 · Veit D. Wild, Robert Hu, Dino Sejdinovic

We develop a framework for generalized variational inference in infinite-dimensional function spaces and use it to construct a method termed Gaussian Wasserstein inference (GWI). GWI leverages the Wasserstein distance be…

Gaussian ProcessesUncertainty QuantificationVariational Inference

Variational Gaussian Process State-Space Models

2014-06-18 · NeurIPS 2014 12 · Roger Frigola, Yutian Chen, Carl E. Rasmussen

State-space models have been successfully used for more than fifty years in different areas of science and engineering. We present a procedure for efficient variational Bayesian learning of nonlinear state-space models b…

Gaussian ProcessesState Space ModelsTime SeriesTime Series Analysis+1

Variational Inference for Gaussian Process Models with Linear Complexity

2017-11-28 · NeurIPS 2017 12 · Ching-An Cheng, Byron Boots

Large-scale Gaussian process inference has long faced practical challenges due to time and space complexity that is superlinear in dataset size. While sparse variational Gaussian process models are capable of learning fr…

Variational Inference

Continual Learning via Sequential Function-Space Variational Inference

2023-12-28 · Tim G. J. Rudner, Freddie Bickford Smith, Qixuan Feng, Yee Whye Teh 외

Sequential Bayesian inference over predictive functions is a natural framework for continual learning from streams of data. However, applying it to neural networks has proved challenging in practice. Addressing the drawb…

Bayesian InferenceContinual LearningSequential Bayesian InferenceVariational Inference

Continual Multi-task Gaussian Processes

2019-10-31 · Pablo Moreno-Muñoz, Antonio Artés-Rodríguez, Mauricio A. Álvarez

We address the problem of continual learning in multi-task Gaussian process (GP) models for handling sequential input-output observations. Our approach extends the existing prior-posterior recursion of online Bayesian in…

Bayesian InferenceContinual LearningGaussian ProcessesStochastic Optimization+1