Meta-learning for mixed linear regression
Jul 12, 2020
Speakers
Weihao Kong
Speaker · 0 followers
Raghav Somani
Speaker · 0 followers
Sham M. Kakade
Speaker · 7 followers
Sewoong Oh
Speaker · 0 followers
About
In modern supervised learning, there are a large number of tasks, but many of them are associated with only a small amount of labelled data. These include data from medical image processing and robotic interaction. Even though each individual task cannot be meaningfully trained in isolation, one seeks to meta-learn across the tasks from past experiences by exploiting some similarities. We study a fundamental question of interest: When can abundant tasks with small data compensate for lack of tasks with big data? We focus on a canonical scenario where each task is drawn from a mixture of k linear regressions, and identify sufficient conditions for such a graceful exchange to hold; the total number of examples necessary with only small data tasks scales similarly as when big data tasks are available. To this end, we introduce a novel spectral approach and show that we can efficiently utilize small data tasks with the help of Ω̃(k^3/2) medium data tasks each with Ω̃(k^1/2) examples.In modern supervised learning, there are a large number of tasks, but many of them are associated with only a small amount of labelled data. These include data from medical image processing and robotic interaction. Even though each individual task cannot be meaningfully trained in isolation, one seeks to meta-learn across the tasks from past experiences by exploiting some similarities. We study a fundamental question of interest: When can abundant tasks with small data compensate for lack of tas…
Categories
AI & Data Science
Category · 10.8k presentations
About ICML 2020
The International Conference on Machine Learning (ICML) is the premier gathering of professionals dedicated to the advancement of the branch of artificial intelligence known as machine learning. ICML is globally renowned for presenting and publishing cutting-edge research on all aspects of machine learning used in closely related areas like artificial intelligence, statistics and data science, as well as important application areas such as machine vision, computational biology, speech recognition, and robotics. ICML is one of the fastest growing artificial intelligence conferences in the world. Participants at ICML span a wide range of backgrounds, from academic and industrial researchers, to entrepreneurs and engineers, to graduate students and postdocs.
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
Character-focused Video Thumbnail Retrieval
Watch later
Improving Sample Quality by Training and Sampli from Latent Energy
Watch later
Learning to Simulate and Design for Structural Engineering
Watch later
Determinantal Point Processes and Randomized Numerical Linear Algebra
Watch later
Gradient-free Online Learning in Games with Delayed Rewards
Watch later
Estimating the Error of Randomized Newton Methods: A Bootstrap Approach
Watch later
Miles Lopes, …