A Proofs As mentioned in sections 3 and 4, our dataset D contains the random perturbation vectors ξ and side information

B.1 Loss function Mathematically, the conditional total variation loss function (11) can be explicitly written as: L The joint loss minimization task is performed using the following network architecture which has 2 parallel networks training simultaneously. The decoder is a mirrored version of the encoder. Here, given the time series nature of the data, we follow the rolling window approach for network training. This is shown in algorithm 2. Once the In this section, we discuss the data generation process for the simulated data used in section 5.1. The data is generated using [Page Jr, 1984].