# Variable-rate analytic array bottleneck

- ID: 2530
- Canonical URL: https://synthcore.org/idea/2530/variable-rate-analytic-array-bottleneck
- API JSON: https://synthcore.org/api/idea/2530.json
- API Markdown: https://synthcore.org/api/idea/2530.md
- Verification status: mech_ok_no_baseline
- Source: [arXiv:2608.18522](https://arxiv.org/abs/2608.18522)
- Category: architecture
- Solves: memory, accuracy, scalability
- ML areas: embedding, quantization, inference-speedup, transformer
- Math tags: linear-algebra, approximation-theory, harmonic-analysis, optimization
- Ratings: usefulness 7/10; difficulty 5/10; novelty 6/10

## Idea description

Replace a fixed-size learned latent for an array-valued complex tensor with a variable-length list of continuous rank-one spectral atoms. An encoder predicts candidate receive direction, transmit direction, residual off-grid offsets, and complex gains; the decoder reconstructs the tensor analytically from the array-response formula, so changing the antenna dimensions does not require changing the decoder weights.

## Mathematical statement

The geometric channel model represents a matrix as a sum of separable atoms: $\mathbf{H}=\sum_{k=1}^{K^{\star}}g_k\mathbf{a}_{N_r}(u_{r,k})\mathbf{a}_{N_t}(u_{t,k})^{\mathsf{H}}$, where $\mathbf{H}\in\mathbb{C}^{N_r\times N_t}$, $K^{\star}$ is the number of physical paths, $g_k\in\mathbb{C}$ is the complex coefficient, $u_{r,k},u_{t,k}\in[-1,1]$ are continuous receive and transmit spatial coordinates, and $\mathbf{a}_N(u)[n]=N^{-1/2}\exp(\mathrm{j}\pi(n-(N-1)/2)u)$ for $n=0,\ldots,N-1$. We exploit this as a structured low-rank dictionary rather than assuming a fixed image-like latent. To correct a predicted coarse coordinate $u$ by an offset $\delta$ without requiring a dense angular grid, use the first-order Taylor approximation $\mathbf{a}_N(u+\delta)\approx\mathbf{a}_N(u)+\delta\mathbf{a}'_N(u)$, with $\mathbf{a}'_N(u)[n]=\mathrm{j}\pi(n-(N-1)/2)\mathbf{a}_N(u)[n]$. For fixed predicted directions, coefficient recovery can use complex ridge least squares: if $\mathbf{y}=\operatorname{vec}(\mathbf{H})$, $\mathbf{A}_{k,:}=\operatorname{vec}(\mathbf{a}_{N_r}(u_{r,k})\mathbf{a}_{N_t}(u_{t,k})^{\mathsf{H}})^{\mathsf{T}}$, and $\mathbf{g}=[g_1,\ldots,g_K]^{\mathsf{T}}$, then $\widehat{\mathbf{g}}=(\mathbf{A}^{\mathsf{H}}\mathbf{A}+\lambda\mathbf{I})^{-1}\mathbf{A}^{\mathsf{H}}\mathbf{y}$, where $\lambda\geq0$ stabilizes nearly collinear atoms.

## Key formulas

- $$\mathbf{a}_{N}(u)[n]=\frac{1}{\sqrt{N}}\exp\left(\mathrm{j}\pi\left(n-\frac{N-1}{2}\right)u\right),\qquad n=0,\ldots,N-1.$$
- $$\mathbf{H}=\sum_{k=1}^{K^{\star}}g_{k}\,\mathbf{a}_{N_{r}}(u_{r,k})\mathbf{a}_{N_{t}}(u_{t,k})^{\mathsf{H}}.$$
- $$\mathbf{a}_{N}(u+\delta)\approx\mathbf{a}_{N}(u)+\delta\mathbf{a}'_{N}(u),\qquad \mathbf{a}'_{N}(u)[n]=\mathrm{j}\pi\left(n-\frac{N-1}{2}\right)\mathbf{a}_{N}(u)[n].$$
- $$\widehat{\mathbf{g}}=(\mathbf{A}^{\mathsf{H}}\mathbf{A}+\lambda\mathbf{I})^{-1}\mathbf{A}^{\mathsf{H}}\operatorname{vec}(\mathbf{H}),\qquad \widehat{\mathbf{H}}=\sum_{k=1}^{K} \widehat g_k\mathbf{a}_{N_r}(\widehat u_{r,k})\mathbf{a}_{N_t}(\widehat u_{t,k})^{\mathsf H}.$$

## Implementation notes

1. Integration point: apply the module immediately after a neural encoder receives a complex matrix or tensor with two array axes, such as a wireless channel, microphone array covariance, radar response, or Fourier-feature map. Split real and imaginary parts and feed them to a small CNN or transformer. The encoder outputs a maximum of $K_{\max}$ slots; each slot predicts an existence logit $s_k$, coarse coordinates $u_{r,k},u_{t,k}\in[-1,1]$, offsets $\delta_{r,k},\delta_{t,k}$ clipped to one grid cell, and a complex coefficient represented by two real numbers. 2. Pseudocode: `z = encoder(real(H), imag(H)); p,u_r,u_t,d_r,d_t,g = heads(z); q=sigmoid(p); ur=clip(u_r+d_r,-1,1); ut=clip(u_t+d_t,-1,1); A_k=vec(a_Nr(ur_k) a_Nt(ut_k).conj().T); g_ls=(A^H A+lambda I)^(-1) A^H vec(H); mask=straight_through_topk_or_concrete(p); Hhat=sum_k mask_k*g_ls[k]*outer(a_Nr(ur_k),a_Nt(ut_k).conj())`. Train with normalized reconstruction loss $\|H-\widehat H\|_F^2/\|H\|_F^2$, an expected-rate penalty $\beta\sum_k q_k$, and coordinate/offset quantization noise during training. 3. Compute the array responses and least-squares solve exactly; estimate no physical path labels. The Taylor derivative can either be used as a differentiable off-grid correction or replaced by the exact exponential at inference. Quantize each active slot using fixed-width coordinates and complex gain, and transmit only active slots. 4. First experiment: use a small $32\times32$ complex channel dataset, compare against a standard autoencoder with a fixed 64- or 128-dimensional latent and against a dense DCT/top-$K$ baseline. Sweep $K_{\max}$ and the rate penalty. Success means lower normalized MSE at equal transmitted bits, graceful degradation as the number of active slots decreases, and transfer from $32\times32$ training to $48\times48$ or $64\times64$ arrays without retraining the encoder heads. Also measure whether the analytic decoder eliminates decoder FLOPs and whether the payload scales with actual spectral complexity rather than always using the maximum latent size.

## Verification

- Status: mech_ok_no_baseline
- Mechanism evidence: yes
- Mechanism confirmed: yes
- Practical verdict: harms
- Verdict: Built and numerically verified the variable-rate analytic-array bottleneck primitives. The Taylor approximation followed the predicted O(delta^2) law (observed slope 1.994 vs 2.0 and coefficient 564.04 vs 564.05), exact K-path ridge recovery reached relative error 1.0e-8 at K=4, and near-duplicate atom conditioning scaled approximately as separation^-2 (observed slope -1.804 vs -2). The analytic greedy codec did not beat the sparse DCT baseline in this small coarse-grid test, so the mechanism is validated but an end-to-end accuracy/rate win was not demonstrated.

### Mechanism check

- Verdict: Built and numerically verified the variable-rate analytic-array bottleneck primitives. The Taylor approximation followed the predicted O(delta^2) law (observed slope 1.994 vs 2.0 and coefficient 564.04 vs 564.05), exact K-path ridge recovery reached relative error 1.0e-8 at K=4, and near-duplicate atom conditioning scaled approximately as separation^-2 (observed slope -1.804 vs -2). The analytic greedy codec did not beat the sparse DCT baseline in this small coarse-grid test, so the mechanism is validated but an end-to-end accuracy/rate win was not demonstrated.
- Confidence: 8/10
- Limitations: No learned neural encoder, quantization, rate penalty, noise robustness, FLOP measurement, or true equal-bit comparison was tested. The atom encoder used a computationally expensive 17x17 coarse grid and greedy pursuit, and the transfer check reused known physical path parameters rather than testing a learned encoder on larger arrays.

### Practical benchmark

- Paired seeds: 8
- Baseline mean: 0
- Idea mean: 0
- p-value: 0.0081
- Paired wins: 0/8
- Benchmark verdict: idea worse (significant)

## Artifacts

- [array_track.py](https://synthcore.org/code/970/array_track.py)
- [bench_report.json](https://synthcore.org/code/970/bench_report.json)
- [experiment.py](https://synthcore.org/code/970/experiment.py)
- [report.md](https://synthcore.org/code/970/report.md)
- [report_bench_2026-09-01T170719.md](https://synthcore.org/code/970/report_bench_2026-09-01T170719.md)
- [results.json](https://synthcore.org/code/970/results.json)
- [run_bench.py](https://synthcore.org/code/970/run_bench.py)
- [Download all files as ZIP](https://synthcore.org/download/970)

## Disclaimer

AI-generated research hypothesis, automatically tested. Not peer-reviewed.