Conditional Risk Minimization for Stochastic Processes

10/09/2015
by   Alexander Zimin, et al.
0

We study the task of learning from non-i.i.d. data. In particular, we aim at learning predictors that minimize the conditional risk for a stochastic process, i.e. the expected loss of the predictor on the next point conditioned on the set of training samples observed so far. For non-i.i.d. data, the training set contains information about the upcoming samples, so learning with respect to the conditional distribution can be expected to yield better predictors than one obtains from the classical setting of minimizing the marginal risk. Our main contribution is a practical estimator for the conditional risk based on the theory of non-parametric time-series prediction, and a finite sample concentration bound that establishes uniform convergence of the estimator to the true conditional risk under certain regularity assumptions on the process.

READ FULL TEXT
research
06/15/2015

Convex Risk Minimization and Conditional Probability Estimation

This paper proves, in very general settings, that convex risk minimizati...
research
01/01/2018

Towards Practical Conditional Risk Minimization

We study conditional risk minimization (CRM), i.e. the problem of learni...
research
08/30/2019

Consistency and Finite Sample Behavior of Binary Class Probability Estimation

In this work we investigate to which extent one can recover class probab...
research
09/19/2020

Suboptimality of Constrained Least Squares and Improvements via Non-Linear Predictors

We study the problem of predicting as well as the best linear predictor ...
research
06/27/2022

Supervised Learning with General Risk Functionals

Standard uniform convergence results bound the generalization gap of the...
research
12/24/2009

On Finding Predictors for Arbitrary Families of Processes

The problem is sequence prediction in the following setting. A sequence ...
research
12/20/2014

Competing with the Empirical Risk Minimizer in a Single Pass

In many estimation problems, e.g. linear and logistic regression, we wis...

Please sign up or login with your details

Forgot password? Click here to reset