Towards Robust Evaluations of Continual Learning
Towards Robust Evaluations of Continual Learning
Sebastian Farquhar and Yarin Gal
2018

Paper summary
natalia
Through a likelihood-focused derivation of a variational inference (VI) loss, Variational Generative Experience Replay (VGER) presents the closest appropriate likelihood- focused alternative to Variational Continual Learning (VCL), the state-of the art prior-focused approach to continual learning.
In non continual learning, the aim is to learn parameters $\omega$ using labelled training data $\mathcal{D}$ to infer $p(y|\omega, x)$. In the continual learning context, instead, the data is not independently and identically distributed (i.i.d.), but may be split into separate tasks $\mathcal{D}_t = (X_t, Y_t)$ whose examples $x_t^{n_t}$ and $y_t^{n_t}$ are assumed to be i.i.d.
In \cite{Farquhar18}, as the loss at time $t$ cannot be estimated for previously discarded datasets, to approximate the distribution of past datasets $p_t(x,y)$, VGER (Variational Generative Experience Replay) trains a GAN $q_t(x, y)$ to produce ($\hat{x}, \hat{y}$) pairs for each class in each dataset as it arrives (generator is kept while data is discarded after each dataset is used). The variational free energy $\mathcal{F}_T$ is used to train on dataset $\mathcal{D}_T$ augmented with samples generated by the GAN. In this way the prior is set as the posterior approximation from the previous task.
Towards Robust Evaluations of Continual Learning

Sebastian Farquhar and Yarin Gal

arXiv e-Print archive - 2018 via Local arXiv

Keywords: stat.ML, cs.LG

**First published:** 2018/05/24 (2 years ago)

**Abstract:** Continual learning experiments used in current deep learning papers do not
faithfully assess fundamental challenges of learning continually, masking
weak-points of the suggested approaches instead. We study gaps in such existing
evaluations, proposing essential experimental evaluations that are more
representative of continual learning's challenges, and suggest a
re-prioritization of research efforts in the field. We show that current
approaches fail with our new evaluations and, to analyse these failures, we
propose a variational loss which unifies many existing solutions to continual
learning under a Bayesian framing, as either 'prior-focused' or
'likelihood-focused'. We show that while prior-focused approaches such as EWC
and VCL perform well on existing evaluations, they perform dramatically worse
when compared to likelihood-focused approaches on other simple tasks.
more
less

Sebastian Farquhar and Yarin Gal

arXiv e-Print archive - 2018 via Local arXiv

Keywords: stat.ML, cs.LG

You must log in before you can submit this summary! Your draft will not be saved!

Preview:

About