/* ---- Google Analytics Code Below */

Saturday, May 23, 2020

How to Learn without Supervision

Ultimately technical, but note the similarity to the alternate ways we learn ... by rote memorization, and the continuous repetition in a contextual background.  Confirmed or not by the context.  Useful for different things.  The latter is more common, but also for different kinds of tasks.

Unsupervised Meta-Learning: Learning to Learn without Supervision
By Benjamin Eysenbach and Abhishek Gupta    May 1, 2020
This post is cross-listed on the CMU ML blog.

The history of machine learning has largely been a story of increasing abstraction. In the dawn of ML, researchers spent considerable effort engineering features. As deep learning gained popularity, researchers then shifted towards tuning the update rules and learning rates for their optimizers. Recent research in meta-learning has climbed one level of abstraction higher: many researchers now spend their days manually constructing task distributions, from which they can automatically learn good optimizers. What might be the next rung on this ladder? In this post we introduce theory and algorithms for unsupervised meta-learning, where machine learning algorithms themselves propose their own task distributions. Unsupervised meta-learning further reduces the amount of human supervision required to solve tasks, potentially inserting a new rung on this ladder of abstraction.

We start by discussing how machine learning algorithms use human supervision to find patterns and extract knowledge from observed data. The most common machine learning setting is regression, where a human provides labels Y for a set of examples X. The aim is to return a predictor that correctly assigns labels to novel examples. Another common machine learning problem setting is reinforcement learning (RL), where an agent takes actions in an environment. In RL, humans indicate the desired behavior through a reward function that the agent seeks to maximize. To draw a crude analogy to regression, the environment dynamics are the examples X, and the reward function gives the labels Y. Algorithms for regression and RL employ many tools, including tabular methods (e.g., value iteration), linear methods (e.g., linear regression) kernel-methods (e.g., RBF-SVMs), and deep neural networks. Broadly, we call these algorithms learning procedures: processes that take as input a dataset (examples with labels, or transitions with rewards) and output a function that performs well (achieves high accuracy or large reward) on the dataset. ... "

No comments: