On the discretization of the object space in inverse problems with application to cryo-electron microscopy

What the math gives to ML

The paper gives a useful interpretation of finite-step EM: under an explicit high-noise condition, the iterate after T+1 updates is asymptotically equivalent to maximizing the likelihood with a reverse-KL barrier toward the uniform simplex point. This provides a principled alternative to tuning an entropy or load-balancing penalty: the number of EM-like routing updates itself controls regularization strength. The most transferable use is calibrating mixture weights or MoE routing probabilities while preventing premature collapse of rarely selected components, especially when component evidence is noisy or nearly indistinguishable.