AI RESEARCH
Distributional Consistency Loss: Beyond Pointwise Data Terms in Inverse Problems
arXiv CS.LG
•
ArXi:2510.13972v2 Announce Type: replace Recovering true signals from noisy measurements is a central challenge in inverse problems spanning medical imaging, geophysics, and signal processing. Current methods balance prior signal priors (regularization) with agreement with noisy data (data-fidelity). Conventional data-fidelity loss functions, such as mean-squared error (MSE) or negative log-likelihood, seek pointwise agreement with noisy measurements, often leading to overfitting to noise.