Learning Time Dependent Choice

09/10/2018
by   Zachary Chase, et al.
0

We explore questions dealing with the learnability of models of choice over time. We present a large class of preference models defined by a structural criterion for which we are able to obtain an exponential improvement over previously known learning bounds for more general preference models. This in particular implies that the three most important discounted utility models of intertemporal choice -- exponential, hyperbolic, and quasi-hyperbolic discounting -- are learnable in the PAC setting with VC dimension that grows logarithmically in the number of time periods. We also examine these models in the framework of active learning. We find that the commonly studied stream-based setting is in general difficult to analyze for preference models, but we provide a redeeming situation in which the learner can indeed improve upon the guarantees provided by PAC learning. In contrast to the stream-based setting, we show that if the learner is given full power over the data he learns from -- in the form of learning via membership queries -- even very naive algorithms significantly outperform the guarantees provided by higher level active learning algorithms.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/02/2023

Agnostic Multi-Group Active Learning

Inspired by the problem of improving classification accuracy on rare or ...
research
10/06/2021

Active Learning for Sound Negotiations

We present two active learning algorithms for sound deterministic negoti...
research
10/10/2018

Batch Active Preference-Based Learning of Reward Functions

Data generation and labeling are usually an expensive part of learning f...
research
06/08/2015

Convergence Rates of Active Learning for Maximum Likelihood Estimation

An active learner is given a class of models, a large set of unlabeled e...
research
06/22/2019

Flattening a Hierarchical Clustering through Active Learning

We investigate active learning by pairwise similarity over the leaves of...
research
03/28/2015

Active Model Aggregation via Stochastic Mirror Descent

We consider the problem of learning convex aggregation of models, that i...
research
05/15/2023

SAT-Based PAC Learning of Description Logic Concepts

We propose bounded fitting as a scheme for learning description logic co...

Please sign up or login with your details

Forgot password? Click here to reset