Causal Learning through Deliberate Undersampling

Sergey Plis | Feb 20, 2023| Publications

Authors : Kseniya Solovyeva, David Danks, Mohammadsajad Abavisani, Sergey Plis

Publication date : 2023/2/20

Journal : Proceedings of Machine Learning Research

Volume : 13

Issue :

Pages :

Publisher : Cambridge MA: JMLR

Description

Domain scientists interested in causal mechanisms are usually limited by the frequency at which they can collect the measurements of social, physical, or biological systems. A common and plausible assumption is that higher measurement frequencies are the only way to gain more informative data about the underlying dynamical causal structure. This assumption is a strong driver for designing new, faster instruments, but such instruments might not be feasible or even possible. In this paper, we show that this assumption is incorrect: there are situations in which we can gain additional information about the causal structure by measuring more than our current instruments. We present an algorithm that uses graphs at multiple measurement timescales to infer underlying causal structure, and show that inclusion of structures at slower timescales can nonetheless reduce the size of the equivalence class of possible causal structures. We provide simulation data about the probability of cases in which deliberate undersampling yields a gain, as well as the size of this gain.

View article

#Paper #Publications

I received my Ph.D. degree in Computer Science in 2007 from The University of New Mexico, Albuquerque, NM, USA. Currently, I am an associate professor of CS at Georgia State University, and the Director of Machine Learning core at the TReNDS institute. My research interests within the fields of machine learning, AI, and data science lie in developing novel and applying existing techniques and approaches to analyzing large scale datasets. One of my key goals is to take advantage of the strengths of multiple data modalities and infer structure and patterns that are hard to obtain non-invasively and/or that are unavailable for direct observation. Ongoing work is focused on inferring multimodal probabilistic and causal descriptions based on fusion of fast and slow imaging modalities. This includes feature estimation via deep learning-based pattern recognition and learning causal graphical models. Besides academia, I’ve led AI research teams developing deep tech AI products including NLP and speech processing solutions that are currently shipped to customers. My research is supported by generous grants from NSF and NIH.

Causal Learning through Deliberate Undersampling

See Also