Michael Wieck-Sosa

I am a third-year PhD Student in the Department of Statistics & Data Science at CMU. I am lucky to be advised by Aaditya Ramdas.

Here is my CV. You can reach me at mwiecksosa AT cmu DOT edu.

I work on nonstationary time series analysis. I am inspired by many topics in statistics and machine learning, notably high-dimensional statistics, nonparametric estimation, causal inference, deep learning, and online learning. I am especially interested in the connections between causality, forecasting, and control.

Working Papers

1. Conditional independence testing with a single realization of a nonstationary nonlinear process (with M. Haddad and A. Ramdas).
   • Summary: We introduce a general framework for conditional independence testing that is robust to both nonstationarity and temporal dependence.
   • Links: Preliminary draft.
2. Identifying relevant forecasting signals in unstable environments (with M. Haddad and A. Ramdas).
   • Summary: We develop a method for detecting new forecasting signals that can be used with nonstationary nonlinear time series.
3. Simulation-based inference for models of complex temporal systems (with C. Shalizi).
   • Summary: We propose a method for inferring the parameters of analytically intractable models of complex temporal systems, drawing from nonstationary nonlinear time series theory.
4. Deep learning for nonstationary nonlinear time series (with W. B. Wu).
   • Summary: We present a theoretical framework for estimating the time-varying regression functions of nonstationary nonlinear time series using deep neural networks.