Solving Second-Order Cone Programs Deterministically in Matrix Multiplication Time
Michelle Wei studied the mathematics of second-order cone programming and found that these problems can be solved more quickly than previously thought by converting the original problem into a modified form which was easier to solve. Problems of this type appear frequently in areas ranging from supply chain optimization to electrical power distribution or machine learning, and she hopes her research may lead to process optimizations across various industries.
View Poster
Michelle Wei, 17, of Saratoga, improved second-order cone programming (SOCP) solvers for her Regeneron Science Talent Search mathematics project. All of math is about problem solving, but the field of optimization is about how to solve problems quickly. Michelle studied SOCP problems, an important topic in convex programming, a field that helps optimize company supply chains, schedule airline flights, and distribute electrical power. Because these problems are so common and critical, understanding how to solve them more quickly is important — and that’s exactly what Michelle did.
In her project, she showed that SOCP problems may always be converted into a modified form that has the same answer but is faster to solve. By solving this modified problem instead of the original, Michelle showed that SOCP problems may be solved more quickly than previously thought.
In San Jose, Michelle attends The Harker School. To lower the energy bills of her parents, Raymond Wei and Sharon Wan, Michelle monitored the power consumption of each appliance in the household using only a single pair of sensors to capture both the frequency and time signature of each one. The A.I. model she created analyzed the results.
Beyond the Project
Michelle studied crystallographic group theory last summer and was struck by how symmetries in crystallographic patterns are echoed everywhere, from the microscopic world of molecular structures to visual arts and architecture.
FUN FACTS: A classically trained pianist, Michelle now reworks familiar tunes of favorite pop-rock songs into melodies she sings and plays to de-stress.
