# Structured Prediction for Conditional Meta-Learning

arXiv: https://arxiv.org/abs/2002.08799 · HTML: https://mlsanity.com/paper/2002.08799/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Feb 2020.

## Built on by (most cited first, 2 of 2)

- [Provable Lifelong Learning of Representations](https://mlsanity.com/paper/2110.14098/) (2021)
- [Conditional Meta-Learning of Linear Representations](https://mlsanity.com/paper/2103.16277/) (2021)

## Abstract (arXiv)

The goal of optimization-based meta-learning is to find a single initialization shared across a distribution of tasks to speed up the process of learning new tasks. Conditional meta-learning seeks task-specific initialization to better capture complex task distributions and improve performance. However, many existing conditional methods are difficult to generalize and lack theoretical guarantees. In this work, we propose a new perspective on conditional meta-learning via structured prediction. We derive task-adaptive structured meta-learning (TASML), a principled framework that yields task-specific objective functions by weighing meta-training data on target tasks. Our non-parametric approach is model-agnostic and can be combined with existing meta-learning methods to achieve conditioning. Empirically, we show that TASML improves the performance of existing meta-learning models, and outperforms the state-of-the-art on benchmark datasets.