Review for NeurIPS paper: Understanding spiking networks through convex optimization

The reviewers expressed some mixed opinions about this work: overall, the idea of interpreting LIF networks as solving quadratic programs (i.e. For example, as R5 noted, the synaptic learning rules currently focus on the feedforward weights rather than the recurrent weights. Moreover, I would add that the recurrent weights are subject to relatively strong low-rank assumptions (specifically, GD is rank M, the dimensionality of the variables being optimized, rather than N, the number of neurons/constraints). This property further implies that the diagonal of the recurrent weights, which determine the reset voltage, are also highly constrained. I think this assumption and its implications warrant further discussion.