paper-with-me

Papers

Continual Learning with Bayesian Neural Networks for Non-Stationary Data

2020-05-01 · ICLR 2020 1 · Richard Kurle, Botond Cseke, Alexej Klushyn, Patrick van der Smagt, Stephan Günnemann

This work addresses continual learning for non-stationary data, using Bayesian neural networks and memory-based online variational Bayes. We represent the posterior approximation of the network weights by a diagonal Gaussian distribution and a complementary memory of raw data. This raw data corresponds to likelihood terms that cannot be well approximated by the Gaussian. We introduce a novel method for sequentially updating both components of the posterior approximation. Furthermore, we propose Bayesian forgetting and a Gaussian diffusion process for adapting to non-stationary data. The experimental results show that our update method improves on existing approaches for streaming data. Additionally, the adaptation methods lead to better predictive performance for non-stationary data.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Continual Learning

Similar Papers 제목 키워드 기반

Bayesian Flow Networks in Continual Learning

2023-10-18 · Mateusz Pyla, Kamil Deja, Bartłomiej Twardowski, Tomasz Trzciński

Bayesian Flow Networks (BFNs) has been recently proposed as one of the most promising direction to universal generative modelling, having ability to learn any of the data type. Their power comes from the expressiveness o…

Bayesian InferenceContinual Learning

Variational Continual Bayesian Meta-Learning

2021-12-01 · NeurIPS 2021 12 · Qiang Zhang, Jinyuan Fang, Zaiqiao Meng, Shangsong Liang 외

Conventional meta-learning considers a set of tasks from a stationary distribution. In contrast, this paper focuses on a more complex online setting, where tasks arrive sequentially and follow a non-stationary distributi…

Meta-LearningTransfer LearningVariational Inference

Learning to Continually Learn with the Bayesian Principle

2024-05-29 · Soochan Lee, Hyeonseong Jeon, Jaehyeon Son, Gunhee Kim

In the present era of deep learning, continual learning research is mainly focused on mitigating forgetting when training a neural network with stochastic gradient descent on a non-stationary stream of data. On the other…

Continual LearningMeta-Learning

Evidence-Informed LLM Beliefs for Continual Scientific Discovery

2026-06-28 · Dhruv Agarwal, Reece Adamson, Andrew McCallum, Peter Clark 외 arxiv

Open-ended scientific discovery with large language models (LLMs) increasingly operates as a long-horizon loop of hypothesis search and verification, where a reward signal guides which hypotheses to test next. A notable …

Task Agnostic Continual Learning Using Online Variational Bayes with Fixed-Point Updates

2020-10-01 · Chen Zeno, Itay Golan, Elad Hoffer, Daniel Soudry

Background: Catastrophic forgetting is the notorious vulnerability of neural networks to the changes in the data distribution during learning. This phenomenon has long been considered a major obstacle for using learning …

Continual Learning