Machine learning emerges from the need to design algorithms that are capable of learning from data how to make accurate predictions and decisions. Such problems arise in a variety of "big data" domains such as finance, genomics, information technologies and neuroscience. Research at ORFE ranges from the design of large-scale machine learning algorithms to their mathematical analysis.

## Research Area Faculty

**Research Interests:** Optimization, dynamical systems, learning for dynamics and control, computational complexity. Applications of these disciplines to optimization problems in systems theory, portfolio management, machine learning, and robotics.

**Research Interests:** Econometrics, statistics, machine learning, data science, causal inference, program evaluation, quantitative methods in the social, behavioral and biomedical sciences.

**Research Interests:** High-dimensional statistics, Machine Learning, financial econometrics, computational biology, biostatistics, graphical and network modeling, portfolio theory, high-frequency finance, time series.

**Research Interests:** Machine learning - theory of neural networks: approximation power, statistical physics of initialization, guarantees for optimization, and generalization Probability - mathematical physics, random matrix theory, Gaussian processes arising in spectral theory/quantum mechanics, and random polynomial

**Research Interests:** Data science, statistical learning, deep learning, decision tree learning; high-dimensional statistics, information theory, statistical physics, network modeling

**Research Interests:** Statistics and Machine Learning

**Research Interests:** Data-driven computational tools for mathematical optimization, machine learning and optimal control. Real-time and embedded optimization. Dynamical systems and optimization-based control. Differentiable optimization. First-order methods for large scale optimization. Machine learning for optimization and…