Learning Curves and Benign Overfitting of Spectral Algorithms in Large Dimensions

ArXi:2604.23212v1 Announce Type: cross Existing large-dimensional theory for spectral algorithms resolves either the optimally tuned point or the interpolation limit, but leaves the under-regularized regime unexplored. We study the learning curve and benign overfitting of spectral algorithms in the large-dimensional setting where the sample size and dimension are of comparable order, i.e., $n \asymp d^{\gamma}$ for some $\gamma>0