- Rating
- 3
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 3
Read review
Paper summary
The authors study analytically the space of solutions of a simple learning problem in a linear rnn (plus a nonlinear case numerically) from the perspective of activity and weight regularization. They characterize two extreme cases where weight or activity cost dominate, and the resulting structure is rank-1 or high-rank, effectively feed-forward, respectively. They validate their findings numerically, compare with the implicit regularization induced by gradient learning, and use an interesting measure of noise-sensitivity based on adjoint states.
Critical strengths
-
The setting is controlled and the problem formulation is very clear
-
The authors use the lambda->0 and lambda>>1 extreme cases to nicely interpolate the other optimal solutions; the emergence of an effective-feed forward structure is explained clearly, as is the conservation law explaining the efficiency/noise-robustness trade-off
Critical weaknesses
-
The novelty wrt Ritter & Chadwick and similar works about low-rank vs feed-forward solutions in rnns needs to be discussed more clearly.
-
the link with signal-to-noise ratio optimization is briefly discussed before equation (7) but should be expanded a bit more
Questions for authors
-
how would you expect the results to change with multiplicative noise?
-
it would be nice to have an additional characterization of the misaligned-coding phenomenon across lambda and gamma, it looks like the effect is way less evident even for a very small adjoint cost
2 comments
I'm happy to recommend acceptance.
Response
We thank the reviewer for their helpful comments and questions, as well as for their appreciation of the merits of our work. We address the points raised under Weaknesses and Questions below:
Novelty wrt Ritter & Chadwick:
We have now expanded the discussion section with an additional sentence clarifying how our paper's findings relate to, yet are substantially distinct from, those of Ritter & Chadwick in lines 482-485: "While [Ritter and Chadwick] also explore the effects of activity regularization numerically, their analytical treatment focuses primarily on characterizing the signal-to-noise performance of working memory networks with different recurrent connectivity patterns, rather than how competing biological costs might preferentially select among them."
SNR optimization instead of absolute noise scale
We have now added a sentence (lines 300-303: "Indeed...variance.") clarifying that for the problem we study, SNR maximization is equivalent to minimizing the absolute noise sensitivity (adjoint cost) that we introduce. Since this point also overlaps with one raised by reviewer
2dwf, we also direct the reviewer's attention to the following point we raised there, repeated below:There is a fairly direct way to massage the tradeoff inequality in Eq. (6) into one relating SNR to activity cost. If the gain g(τ) is allowed to be optimized as well (otherwise SNR is effectively identical to inverse absolute noise), then we straightforwardly obtain by similar arguments that ExEq(τ)≥g(τ)2τ2, where Eq(τ)=∫0τ∥q(t)∥2dt, and thus can upper bound SNR(τ)=ση2Eq(τ)g(τ)2 as SNR(τ)≤ση2τ21Ex. Morally, this is expressing a similar fundamental constraint as what we state: to achieve high SNR, one needs to pay in activity cost.
Multiplicative noise:
Under the most natural/simple model of multiplicative noise, where the input noise entering the model is given by x(t)⊙η(t), we suspect that this would weaken, but not entirely ablate, the tradeoff between activity efficiency and noise robustness. This is because lower activity would also reduce the scale of the injected noise, thereby making noise robustness and activity efficiency more ``aligned" as objectives. We leave this question to future work.
Effect of (λ, γ) on misaligned coding:
The reviewer is correct in that introducing an adjoint cost can substantially dampen the misaligned coding phenomena observed, as reported in Fig. E.1. However, based on analysis of both the idealized linear setting and in the nonlinear ALM experiments, the emergence of at least some degree of misaligned coding with small λ remains robust to the introduction of process noise. This remains true whether the noise is introduced indirectly through the γ-weighted adjoint cost or directly through adding noise to the dynamics itself, as was done in the ALM experiments. Nonetheless, we agree that a more detailed investigation of the entire (λ,γ) plane and its modulation of misaligned coding phenomena would also be a useful direction for future work.