Learning to Stop While Learning to Predict

06/09/2020
by   Xinshi Chen, et al.
8

There is a recent surge of interest in designing deep architectures based on the update steps in traditional algorithms, or learning neural networks to improve and replace traditional algorithms. While traditional algorithms have certain stopping criteria for outputting results at different iterations, many algorithm-inspired deep models are restricted to a “fixed-depth” for all inputs. Similar to algorithms, the optimal depth of a deep architecture may be different for different input instances, either to avoid “over-thinking”, or because we want to compute less for operations converged already. In this paper, we tackle this varying depth problem using a steerable architecture, where a feed-forward deep model and a variational stopping policy are learned together to sequentially determine the optimal number of layers for each input instance. Training such architecture is very challenging. We provide a variational Bayes perspective and design a novel and effective training procedure which decomposes the task into an oracle model learning stage and an imitation stage. Experimentally, we show that the learned deep model along with the stopping policy improves the performances on a diverse set of tasks, including learning sparse recovery, few-shot meta learning, and computer vision tasks.

READ FULL TEXT

page 8

page 14

page 15

research
05/05/2021

Learning Algorithms for Regenerative Stopping Problems with Applications to Shipping Consolidation in Logistics

We study regenerative stopping problems in which the system starts anew ...
research
08/03/2022

Improving Meta-Learning Generalization with Activation-Based Early-Stopping

Meta-Learning algorithms for few-shot learning aim to train neural netwo...
research
02/20/2022

On Optimal Early Stopping: Over-informative versus Under-informative Parametrization

Early stopping is a simple and widely used method to prevent over-traini...
research
12/13/2019

Meta-Learning Initializations for Image Segmentation

While meta-learning approaches that utilize neural network representatio...
research
01/20/2022

DDPG-Driven Deep-Unfolding with Adaptive Depth for Channel Estimation with Sparse Bayesian Learning

Deep-unfolding neural networks (NNs) have received great attention since...
research
05/20/2022

UViM: A Unified Modeling Approach for Vision with Learned Guiding Codes

We introduce UViM, a unified approach capable of modeling a wide range o...
research
06/19/2017

Unsure When to Stop? Ask Your Semantic Neighbors

In iterative supervised learning algorithms it is common to reach a poin...

Please sign up or login with your details

Forgot password? Click here to reset