Supplementary Material of Unsupervised Learning From Incomplete Measurements for Inverse Problems

The proof of Theorem 4.2 in the main paper uses the following technical lemma: Lemma 1.1 (Lemmas 4.5 and 4.6 in [1]). The proof of Lemma 1.1 follows standard covering arguments and may be sketched as follows. Full details can be found in the proofs in [1]. We can now present the proof of Theorem 4.2: Proof. X } (3) is empty, where \ denotes set difference.