TY - GEN
T1 - Gaussian Graphical Model Selection from Size Constrained Measurements
AU - Dasarathy, Gautam
PY - 2019/7
Y1 - 2019/7
N2 - In this paper, we introduce the problem of learning graphical models from size constrained measurements. This is inspired by a wide range of problems where one is unable to measure all the variables involved simultaneously. We propose notions of data requirement for this setting and then begin by considering an extreme case where one is allowed to only measure pairs of variables. For this setting we propose a simple algorithm and provide guarantees on its behavior. We then generalize to the case where one is allowed to measure up to r variables simultaneously, and draw connections to the field of combinatorial designs. Finally, we propose an interactive version of the proposed algorithm that is guaranteed to have significantly better data requirement on a wide range of realistic settings.
AB - In this paper, we introduce the problem of learning graphical models from size constrained measurements. This is inspired by a wide range of problems where one is unable to measure all the variables involved simultaneously. We propose notions of data requirement for this setting and then begin by considering an extreme case where one is allowed to only measure pairs of variables. For this setting we propose a simple algorithm and provide guarantees on its behavior. We then generalize to the case where one is allowed to measure up to r variables simultaneously, and draw connections to the field of combinatorial designs. Finally, we propose an interactive version of the proposed algorithm that is guaranteed to have significantly better data requirement on a wide range of realistic settings.
KW - active learning
KW - combinatorial designs
KW - Gaussian graphical models
KW - sample complexity
UR - http://www.scopus.com/inward/record.url?scp=85073155023&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85073155023&partnerID=8YFLogxK
U2 - 10.1109/ISIT.2019.8849299
DO - 10.1109/ISIT.2019.8849299
M3 - Conference contribution
AN - SCOPUS:85073155023
T3 - IEEE International Symposium on Information Theory - Proceedings
SP - 1302
EP - 1306
BT - 2019 IEEE International Symposium on Information Theory, ISIT 2019 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2019 IEEE International Symposium on Information Theory, ISIT 2019
Y2 - 7 July 2019 through 12 July 2019
ER -