Poster
Optimization over Sparse Support-Preserving Sets: Two-Step Projection with Global Optimality Guarantees
William de Vazelhes · Xiaotong Yuan · Bin Gu
West Exhibition Hall B2-B3 #W-515
Many real-world problems, from sensor selection to feature selection in machine learning, involve picking just a few important variables while meeting additional conditions. This is called “sparse optimization with constraints.” Solving such problems can be tricky, especially when the usual mathematical tools don’t work well due to complex requirements.Our work introduces a new algorithm that can handle these situations more effectively. It builds on a popular method called iterative hard thresholding but adapts it to deal with both sparsity and additional constraints by breaking the problem into two simple steps.We also developed simpler and more extensible mathematical tool to help analyze how well the algorithm performs, improving on previous results.This work helps make powerful optimization techniques more widely usable in practical, real-world situations.