Stochastic Multiple Choice Learning for Training Diverse Deep Ensembles

by   Stefan Lee, et al.

Many practical perception systems exist within larger processes that include interactions with users or additional components capable of evaluating the quality of predicted solutions. In these contexts, it is beneficial to provide these oracle mechanisms with multiple highly likely hypotheses rather than a single prediction. In this work, we pose the task of producing multiple outputs as a learning problem over an ensemble of deep networks -- introducing a novel stochastic gradient descent based approach to minimize the loss with respect to an oracle. Our method is simple to implement, agnostic to both architecture and loss function, and parameter-free. Our approach achieves lower oracle error compared to existing methods on a wide range of tasks and deep architectures. We also show qualitatively that the diverse solutions produced often provide interpretable representations of task ambiguity.



There are no comments yet.


page 2

page 6

page 7


Gradient-Based Empirical Risk Minimization using Local Polynomial Regression

In this paper, we consider the problem of empirical risk minimization (E...

Why M Heads are Better than One: Training a Diverse Ensemble of Deep Networks

Convolutional Neural Networks have achieved state-of-the-art performance...

Confident Multiple Choice Learning

Ensemble methods are arguably the most trustworthy techniques for boosti...

On the Effectiveness of Mode Exploration in Bayesian Model Averaging for Neural Networks

Multiple techniques for producing calibrated predictive probabilities us...

L4: Practical loss-based stepsize adaptation for deep learning

We propose a stepsize adaptation scheme for stochastic gradient descent....

Speeding Up Iterative Closest Point Using Stochastic Gradient Descent

Sensors producing 3D point clouds such as 3D laser scanners and RGB-D ca...

The Shooting Regressor; Randomized Gradient-Based Ensembles

An ensemble method is introduced that utilizes randomization and loss fu...

Code Repositories


GRoup Emotion Parser: A random recurrent deep ensemble based feature extraction framework.

view repo
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.