Erratum: Deep Equilibrium Models for Poisson Imaging Inverse Problems via Mirror Descent
the variational calculus primitives and a full proof of the abstract Kurdyka–Łojasiewicz (KŁ) convergence theorem (Theorem A.8 of Attouch, Bolte, and Svaiter);
the Poisson/Kullback–Leibler variational setup with zero counts permitted (\(y_i \ge 0\)), the counterexample (Example 1) showing that the classical Burg entropy gradient fails to be Lipschitz continuous on sublevel sets \(L_0\), and the shifted Burg geometry (\(h_\xi \), \(D_{h_\xi }\)) yielding the variational equivalence \((1) \iff (4) \iff (5)\);
sublevel separation from the boundary singular set and relative smoothness \(L_\beta h_\xi - F\) convex on \(K_\beta \) (Lemma 2);
single-step positivity of denominators, sublevel invariance, Bregman sufficient decrease (6), and relative error bound (7) (Lemma 3), followed by constant-step sequence convergence (Theorem 4, passing the definable KŁ property \(\mathrm{HasKL}(\Psi )\) as an explicit hypothesis);
monotone backtracking step-size stabilization and global convergence (Algorithm 1).