# LQ-Compressed LPV Latent Rollouts

- ID: 1540
- Canonical URL: https://synthcore.org/idea/1540/lq-compressed-lpv-latent-rollouts
- API JSON: https://synthcore.org/api/idea/1540.json
- API Markdown: https://synthcore.org/api/idea/1540.md
- Verification status: failed_benchmark
- Source: [arXiv:2607.28490](https://arxiv.org/abs/2607.28490)
- Category: dynamics
- Solves: stability, scalability, inference-speedup
- ML areas: world-model, rnn, ssm, inference-speedup
- Math tags: control-theory, dynamical-systems, linear-algebra, optimization
- Ratings: usefulness 7/10; difficulty 6/10; novelty 6/10

## Idea description

Replace a neural sequence model's unconstrained multi-step latent rollout with a data-driven LPV predictor acting on a learned latent state. Build the predictor from Hankel matrices of past latent observations, inputs, and scheduling features, then use an LQ factorization to project the large data coefficient matrix into a fixed-dimensional coordinate system. The model preserves scheduling-conditioned dynamics while making rollout cost independent of the number of training trajectories.

## Mathematical statement

For a latent or observed signal with past horizon M and prediction horizon T, let x_k^0 denote the initial latent state reconstructed from past data, z_k^P the lifted past input-output-scheduling vector, u_k^F the future input sequence, and e_k^F future innovation variables. The LPV subspace predictor is y_[k,k+T-1]=Gamma_x x_k^0+Gamma_z z_k^P+H_d u_k^F+H_s e_k^F, where Gamma_x, Gamma_z, H_d, and H_s are multi-step observability, past-data, future-input, and innovation operators. Given a data matrix D formed by stacked Hankel rows, estimate K from Y_F approximately equal to K D, where Y_F is the future latent-output Hankel matrix. Compute an LQ factorization D=LQ with Q having orthonormal rows, retain a numerical rank r, and use K L as the compressed predictor coordinate. The online coordinate dimension is r rather than the number of data columns. The discarded projection error is controlled by the tail singular values of the retained matrix.

## Key formulas

- $$y_{[k,k+T-1]}=\Gamma_xx_k^0+\Gamma_zz_k^P+\mathcal{H}_du_k^F+\mathcal{H}_se_k^F.$$
- $$Y_F\approx K D,\qquad D=LQ,\qquad QQ^{\top}=I.$$
- $$\widehat{Y}_F=K L\,Qd_k.$$
- $$\|Y_F-\widehat{Y}_{F,r}\|_F^2\ \text{is expected to scale with}\ \sum_{i>r}\sigma_i^2(KL).$$

## Implementation notes

1. Exact integration point: use this as the rollout head of a latent world model or recurrent state-space model. An encoder maps observations to latent vectors; concatenate latent states, controls, and scheduling features into the past data vector. Initially keep the encoder fixed or pretrained, and replace only the multi-step prediction head. 2. Pseudocode: collect trajectories; construct aligned Hankel columns d_j from past latent states, past inputs, future scheduling variables, and candidate future controls; construct Y_F from future latent states; fit K=Y_F D^T(DD^T+lambda I)^(-1); compute an LQ or QR factorization of D; retain rank r using a singular-value threshold; and train or fine-tune the encoder with multi-step loss ||Y_F-K_rD||_F^2 plus decoded observation loss. During inference, form the current past vector, project it using the retained factors, and recursively predict the next T latent states. 3. Computed from the paper: the separation into past, future-input, scheduling, and innovation blocks and the LQ compression. Estimated empirically: latent dimension, ridge coefficient lambda, retained rank r, and whether innovations are set to zero, sampled, or produced by a learned noise head. 4. First cheap experiment: train a small GRU baseline and this compressed LPV latent predictor on Lorenz-63 or cart-pole trajectories with a measured time-varying parameter. Compare 10-, 25-, and 50-step rollout error, wall-clock inference, and parameter count for r in {4,8,16,32}. The prediction is that error decreases until the singular-value elbow, while online cost remains nearly constant as the number of stored trajectories grows; the measured Frobenius error should track the singular-value tail within about 20%.

## Verification

- Status: failed_benchmark
- Mechanism evidence: yes
- Mechanism confirmed: no
- Practical verdict: inconclusive
- Verdict: Built an LQ-compressed LPV latent-rollout toy predictor with synthetic scheduling-conditioned dynamics. The core mechanism was confirmed: compression error matched the omitted squared singular-value tail to numerical precision, decreased monotonically with rank, and vanished at numerical rank. The compressed operator shape stayed fixed as training columns increased from 200 to 5000; rank 16 matched the full ridge predictor essentially exactly, although this toy did not establish a meaningful wall-clock speedup.

### Mechanism check

- Verdict: Built an LQ-compressed LPV latent-rollout toy predictor with synthetic scheduling-conditioned dynamics. The core mechanism was confirmed: compression error matched the omitted squared singular-value tail to numerical precision, decreased monotonically with rank, and vanished at numerical rank. The compressed operator shape stayed fixed as training columns increased from 200 to 5000; rank 16 matched the full ridge predictor essentially exactly, although this toy did not establish a meaningful wall-clock speedup.
- Confidence: 8/10
- Limitations: This is a synthetic observed-state LPV toy, not a learned encoder, GRU, Lorenz-63/cart-pole benchmark, or decoded neural world model. It fits one multi-step horizon of 10 rather than true recursive 10/25/50-step rollouts, does not model innovations, and does not provide a robust repeated timing benchmark or GPU comparison; the singular-tail identity is exact for the constructed orthonormal LQ coordinates.

### Practical benchmark

- Paired seeds: 8
- Baseline mean: 0
- Idea mean: 0
- p-value: 0.1255
- Paired wins: 3/8
- Benchmark verdict: no significant win

## Artifacts

- [bench_report.json](https://synthcore.org/code/475/bench_report.json)
- [lq_lpv_experiment.py](https://synthcore.org/code/475/lq_lpv_experiment.py)
- [report.md](https://synthcore.org/code/475/report.md)
- [report_bench_2026-08-31T141908.md](https://synthcore.org/code/475/report_bench_2026-08-31T141908.md)
- [results.json](https://synthcore.org/code/475/results.json)
- [stage2_lq_lpv.py](https://synthcore.org/code/475/stage2_lq_lpv.py)
- [Download all files as ZIP](https://synthcore.org/download/475)

## Disclaimer

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