BAM: Bayes Augmented with Memory
Online learning via Bayes' theorem allows new data to be continuously integrated into an agent's current beliefs. However, a naive application of Bayesian methods in non-stationary environments leads to slow adaptation and results in state estimates that may converge confidently to the wrong parameter value. A common solution when learning in changing environments is to discard/downweight past data; however, this simple mechanism of ``forgetting'' fails to account for the fact that many real-world environments involve revisiting similar states. We propose a new framework, Bayes augmented with memory (BAM), that takes advantage of past experience by allowing the agent to choose which past observations to remember and which to forget. We demonstrate that BAM generalizes many popular Bayesian update rules for non-stationary environments. Through a variety of experiments, we demonstrate the ability of BAM to continuously adapt in an ever-changing world.
Code (0)
등록된 구현이 없습니다.
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Learning-augmented count-min sketches via Bayesian nonparametrics
The count-min sketch (CMS) is a time and memory efficient randomized data structure that provides estimates of tokens' frequencies in a data stream of tokens, i.e. point queries, based on random hashed data. A learning-a…
A New Hierarchical Redundancy Eliminated Tree Augmented Naive Bayes Classifier for Coping with Gene Ontology-based Features
The Tree Augmented Naive Bayes classifier is a type of probabilistic graphical model that can represent some feature dependencies. In this work, we propose a Hierarchical Redundancy Eliminated Tree Augmented Naive Bayes …
BERAG: Bayesian Ensemble Retrieval-Augmented Generation for Knowledge-based Visual Question Answering
A common approach to question answering with retrieval-augmented generation (RAG) is to concatenate documents into a single context and pass it to a language model to generate an answer. While simple, this strategy can o…
Visual Question AnsweringPersonalized LLM Response Generation with Parameterized Memory Injection
Large Language Models (LLMs) have exhibited remarkable proficiency in comprehending and generating natural language. On the other hand, personalized LLM response generation holds the potential to offer substantial benefi…
Bayesian Optimisationparameter-efficient fine-tuningResponse GenerationPositive Feature Values Prioritized Hierarchical Redundancy Eliminated Tree Augmented Naive Bayes Classifier for Hierarchical Feature Spaces
The Hierarchical Redundancy Eliminated Tree Augmented Naive Bayes (HRE-TAN) classifier is a semi-naive Bayesian model that learns a type of hierarchical redundancy-free tree-like feature representation to estimate the da…