mirca Goto Github PK

I graduated with a PhD from the Department of Electronic and Computer Engineering at HKUST, in sunny Hong Kong, where I was a member of the Convex Optimization in Finance Group advised by Prof Daniel Palomar.

My PhD research focused on problems involving graphs, where I designed optimization algorithms combined with elements of graph theory and statistical learning theory, to extract knowledge from networks of financial assets. Our research results during my PhD were published in venues such as NeurIPS, ICML, JMLR, AISTATS, and AAAI. I also served as a reviewer for NeurIPS, ICML, ICLR, JMLR, and IEEE TNNLS.

I have done a number of internships along the way:

• equity quant at Merrill Lynch: wrote code for portfolio risk optimization and limit order book forecasting;
• research scientist at Shell Street Labs: wrote code for portfolio strategy optimization;
• scientific software engineer at National Aeronautics and Space Administration (NASA): part of the lead developers team of lightkurve, an open source package for time series analysis of NASA Kepler, K2, & TESS data;
• Google Summer of Code developer for OpenAstronomy: improved the point spread function photometry capabilities of photutils;
• guest researcher at National Institute of Standards and Technology (NIST): research on nanophotonics published in Nature and Review of Scientific Instruments;

Nowdays, I work as a Quantitative Trader at Merril Lynch (Bank of America).

Here's a list of selected papers that I published together with my co-authors during my PhD:

• Adaptive Estimation of Graphical Models under Total Positivity, ICML 2023
• Fast Projected Newton-like Method for Precision Matrix Estimation under Total Positivity, NeurIPS 2023
• Learning Bipartite Graphs: Heavy Tails and Multiple Components, NeurIPS 2022
• Graphical Models in Heavy-Tailed Markets, NeurIPS 2021
• Nonconvex Sparse Graph Learning under Laplacian Constrained Graphical Model, NeurIPS 2020
• Structured Graph Learning Via Laplacian Spectral Constraints, NeurIPS 2019

• riskparity.py: performant code for constructing optimal risk parity portfolios in Python
• fingraph: estimating networks of financial assets in R
• bipartite: estimating bipartite graphs with applications to asset classification in R

I spend most of my time doing research and coding. Outside of that, I love swimming and crab hunting in the waters of Clear Water Bay and video-chatting with my nephew Chico and my dog Pluto.