3 papers
cs.LG2026
An accurate flatness measure to estimate the generalization performance of CNN models
Rahman Taleghani, Maryam Mohammadi, Francesco Marchetti
Flatness measures based on the spectrum or the trace of the Hessian of the loss are widely used as proxies for the generalization ability of deep networks. However, most existing d…
math.NA2025
Weak convergence rates for spectral regularization via sampling inequalities
Sabrina Guastavino, Gabriele Santin, Francesco Marchetti +1
Convergence rates in spectral regularization methods quantify the approximation error in inverse problems as a function of the noise level or the number of sampling points. Classic…
math.NA2025
Tuning Butterworth filter's parameters in SPECT reconstructions via kernel-based Bayesian optimization with a no-reference image evaluation metric
Luca Pastrello, Diego Cecchin, Gabriele Santin +1
In Single Photon Emission Computed Tomography (SPECT), the image reconstruction process involves many tunable parameters that have a significant impact on the quality of the result…