[CS330] 03. Supervised solution of Meta-learning problem: Black-Box vs. Optimization-based vs. Non-Parametric

The Meta-Learning Problem

Given data from $\mathcal{T}_1, \cdots, \mathcal{T}_n$, quickly solve new task $\mathcal{T}_\textrm{test}$.

Assume that meta-training tasks and meta-test task drawn i.i.d. from same task distribution. 

$\mathcal{T}_1, \cdots, \mathcal{T}_n \sim p(\mathcal{T}), \mathcal{T}_j \sim p(\mathcal{T})$

For example, the task can be: a robot performing different tasks or giving feedback to students on different exams.

• k-shot learning: learning with k examples per class (or k examples total for regression)
• N-way classification: choosing between N classes
• k-shot N-way learning: 

General recipe for Meta-Learning problem

Black-box Adaptation approach

 

Optimization-based Adaptation approach

 

Black-box vs. Optimization-based

Non-Parametric