02152ntm a22003137a 4500
374025
374025
AT-ISTA
20190822082631.0
190822s2018 au ||||| m||| 00| 0 eng d
IST
Zimin, Alexander
4470
Learning from dependent data
IST Austria
2018
Thesis
Abstract
Acknowledgements
About the Author
List of Figures
1 Introduction
2 Background
3 Theory of Conditional Risk Minimization
4 Conditional risk Minimization in Practice
5 Online Multi-task learning
6 Conclusion and Future Work
Bibliography
A Proofs from Chapter 3
The most common assumption made in statistical learning theory is the assumption of the independent and identically distributed (i.i.d.) data. While being very convenient mathematically, it is often very clearly violated in practice. This disparity between the machine learning theory and applications underlies a growing demand in the development of algorithms that learn from dependent data and theory that can provide generalization guarantees similar to the independent situations. This thesis is dedicated to two variants of dependencies that can arise in practice. One is a dependence on the level of samples in a single learning task. Another dependency type arises in the multi-task setting when the tasks are dependent on each other even though the data for them can be i.i.d. In both cases we model the data (samples or tasks) as stochastic processes and introduce new algorithms for both settings that take into account and exploit the resulting dependencies. We prove the theoretical guarantees on the performance of the introduced algorithms under different evaluation criteria and, in addition, we compliment the theoretical study by the empirical one, where we evaluate some of the algorithms on two real world datasets to highlight their practical applicability.
https://doi.org/10.15479/AT:ISTA:TH1048
ddc
0
0
ddc
0
0
LIB
LIB
2019-08-22
AT-ISTA#001881
2019-08-22
2019-08-22
BOOK