Continual learning: a feature extraction formalization, an efficient algorithm, and fundamental obstructions

By Binghui Peng, Andrej Risteski. 2022

16 citations recorded by the source corpus.

Continual learning is an emerging paradigm in machine learning, wherein a model is exposed in an online fashion to data from multiple different distributions (i.e. environments), and is expected to adapt to the distribution change. Precisely, the goal is to perform well in the new environment, while simultaneously retaining the performance on the previous environments (i.e. avoid"catastrophic forgetting") -- without increasing the size of the model. While this setup has enjoyed a lot of attention in the applied community, there hasn't be theoretical work that even formalizes the desired guarantees. In this paper, we propose a framework for continual learning through the framework of feature extraction -- namely, one in which features, as well as a classifier, are being trained with each environment. When the features are linear, we design an efficient gradient-based algorithm $\mathsf{DPGD}$, that is guaranteed to perform well on the current environment, as well as avoid catastrophic forgetting. In the general case, when the features are non-linear, we show such an algorithm cannot exist, whether efficient or not.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Meta & Continual Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. René Vidal
  2. Paris V. Giampouras
  3. Liangzu Peng

In Computer Vision and Pattern Recognition

  1. René Vidal
  2. Paris V. Giampouras
  3. Liangzu Peng
  4. Ehsan Elhamifar
  5. Paolo Favaro
  6. Shuicheng Yan
  7. Zhouchen Lin
  8. Jitendra Malik

In Meta & Continual Learning

  1. René Vidal
  2. Paris V. Giampouras
  3. Liangzu Peng

Citations in the corpus