> For the complete documentation index, see [llms.txt](https://lichangbin.gitbook.io/paper_notes/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://lichangbin.gitbook.io/paper_notes/oct/continuous-meta-learning-without-tasks.md).
# Continuous Meta Learning without tasks
## Motivation
Meta-learning is a promising strategy for learning to efficiently learn within new tasks, using data gathered from a distribution of tasks.
However, the meta-learning literature thus far has focused on the task segmented setting, where at train-time, offline data is assumed to be split according to the underlying task, and at test-time, the algorithms are optimized to learn in a single task.
In this work, we enable the application of generic meta-learning algorithms to settings where this task segmentation is unavailable, such as continual online learning with a time-varying task.
We present meta-learning via online changepoint analysis (MOCA), an approach which augments a meta-learning algorithm with a differentiable Bayesian changepoint detection scheme.
## Problem Statement
We assume that we have access to a representative time series generated in the same manner from the same distribution of tasks, and use this time series to optimize in an offline, meta-training phase.
Critically, however, in stark contrast to standard meta-learning approaches, we do not assume access to task segmentation.
Moreover, we highlight that we consider the case of individual data points provided sequentially, in contrast to the common “k-shot, n-way” problem setting prevalent in few-shot learning (especially classification).
## Bayesian Online Changepoint Detection (BOCPD)
We build on Bayesian online changepoint detection (Adams & MacKay, 2007), an approach for detecting changepoints (i.e. task switches) originally presented in a streaming unconditional density estimation context.
BOCPD operates by maintaining a belief distribution over run lengths, i.e. how many of the past data points $$y\_t$$ correspond to the current task.
In this work, we extend this approach of Adams & MacKay (2007) beyond Bayesian unconditional density estimation to apply to general meta-learning models operating in the conditional density estimation setting.
Details could be found from: [http://gregorygundersen.com/blog/2019/08/13/bocd/
]()
## Overview of MOCA
## Meta-Learning via Online Changepoint Analysis
#### NOTE: Adding more about Connection with meta-learning, online learning, and continual learning
## Reference
* (latest version)