- Rating
- 1
- Confidence
- 4
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
The paper proposes a “fully unitary” quantum backpropagation scheme for deep QNNs. The idea is a forward pass alternating weight unitaries with QSVT-implemented activations and a Heisenberg-picture propagation of the loss operator. The paper claims that a per-iteration gate bound.
Empirically, it reports MNIST-parity results against the MoQE baseline and 98.2% accuracy.
Critical strengths
The problem is very important I believe. I liked the Heisenberg-picture framing as a reasonable starting point. The paper tries to address a comprehensive study of the topic including convergence analysis, BP analysis, and complexity.
Critical weaknesses
It seems that paper is assuming the existence of a unitary nonlinear activation. QSVT applies a polynomial to the singular values of a fixed block-encoded matrix , which is again a linear map. Iit does not apply a sigmoid entrywise to amplitudes. It is not clear to me whether the paper considers this or not. Specially since it says in Sec. 3.2 that a circuit without inter-layer non-linearity collapses to a single unitary. So even with QSVT we still get unitary.
Each gradient component is a scalar expectation value usually. Applying a QSVT polynomial of a block-encoding of G to produces the vector not an expectation value ! Writing an expectation value into a register coherently is amplitude estimation, which costs queries per component and must be repeated per parameter. The paper never shows how queries yield this.
The forward pass is said to cache both and , which are two different states obtained from one copy. Holding both requires two copies. Holding all 2L cached states simultaneously requires 2L independent forward evaluations. Abbas et al. (2023) prove lower bounds on exactly this information-reuse problem; the submission must explain where its model escapes those bounds, and it does not.
Questions for authors
Q1. Is a fixed unitary or state-dependent? If fixed, where is the nonlinearity? If state-dependent, how are the amplitudes of obtained?
Q2. Can you give the explicit circuit that maps for parameters with block-encoding queries, including how the register contents are read?