Robust Meta-learning for Mixed Linear Regression with Small Batches

06/17/2020
by   Weihao Kong, et al.
29

A common challenge faced in practical supervised learning, such as medical image processing and robotic interactions, is that there are plenty of tasks but each task cannot afford to collect enough labeled examples to be learned in isolation. However, by exploiting the similarities across those tasks, one can hope to overcome such data scarcity. Under a canonical scenario where each task is drawn from a mixture of k linear regressions, we study a fundamental question: can abundant small-data tasks compensate for the lack of big-data tasks? Existing second moment based approaches show that such a trade-off is efficiently achievable, with the help of medium-sized tasks with Ω(k^1/2) examples each. However, this algorithm is brittle in two important scenarios. The predictions can be arbitrarily bad (i) even with only a few outliers in the dataset; or (ii) even if the medium-sized tasks are slightly smaller with o(k^1/2) examples each. We introduce a spectral approach that is simultaneously robust under both scenarios. To this end, we first design a novel outlier-robust principal component analysis algorithm that achieves an optimal accuracy. This is followed by a sum-of-squares algorithm to exploit the information from higher order moments. Together, this approach is robust against outliers and achieves a graceful statistical trade-off; the lack of Ω(k^1/2)-size tasks can be compensated for with smaller tasks, which can now be as small asO(log k).

READ FULL TEXT

page 1

page 2

page 3

page 4

02/20/2020

Meta-learning for mixed linear regression

In modern supervised learning, there are a large number of tasks, but ma...
01/01/2017

Outlier Robust Online Learning

We consider the problem of learning from noisy data in practical setting...
06/17/2022

Riemannian CUR Decompositions for Robust Principal Component Analysis

Robust Principal Component Analysis (PCA) has received massive attention...
07/12/2020

A spectral algorithm for robust regression with subgaussian rates

We study a new linear up to quadratic time algorithm for linear regressi...
06/30/2021

Robust Coreset for Continuous-and-Bounded Learning (with Outliers)

In this big data era, we often confront large-scale data in many machine...
11/19/2015

Robust Classification by Pre-conditioned LASSO and Transductive Diffusion Component Analysis

Modern machine learning-based recognition approaches require large-scale...