cs.LGApr 5, 2025

Local-Order Auxiliary Losses Can Improve Autoencoder Reconstruction

Authors: Harvey Dam, Martin Burtscher, Tripti Agarwal, Ganesh Gopalakrishnan

Organizations: Kahlert School of Computing University of Utah Salt Lake City, UT, USA · Department of Computer Science Texas State University San Marcos, TX, USA

Abstract

Mean-squared error is the default objective for training autoencoders, yet compressed reconstructions often depend not only on pointwise accuracy but also on preserving local spatial order. We study whether structural auxiliary losses can improve, rather than trade off against, MSE in finite-capacity autoencoders. We introduce finite-difference sign error (FDSE), a local-order auxiliary objective that penalizes disagreements between the signs of neighboring finite differences in the target and reconstruction. FDSE is simple, architecture-agnostic, and differentiable through smooth sign surrogates. Across four tensor reconstruction tasks, we find that moderate mixtures of MSE and FDSE can substantially reduce validation MSE relative to pure MSE training. In coefficient sweeps, FDSE mixtures reduce validation MSE by 2.3×\times--7.0×\times over pure MSE on these tasks, while comparisons with other auxiliary objectives show FDSE to be among the strongest structural objectives tested. The effect is not universal: pure FDSE performs poorly, and gains are largest for coherent spatial fields where local order carries information about the underlying signal. These results suggest that, in compressed-latent reconstruction, appropriately weighted local-structure supervision can guide optimization toward solutions with better pointwise accuracy, rather than merely improving perceptual or structural metrics at MSE's expense.

Figures & tables

Appendix figures & tables10 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

Sep 26, 2026

Self-Reconstruction Dynamics for Autoencoder Reconstruction Refinement

Standard autoencoder (AE) inference uses a single encoder-decoder pass, though the latent may not be optimal for each sample under a fixed decoder. We ask whether a trained AE can reveal information for improving its own reconstruction. Repeated application of a frozen AE to its reconstruction produces transient image- and latent-space trajectories, termed Self-Reconstruction Dynamics (SRD). Although this degrades fidelity in the AEs studied here, SRD contains sample-specific information for correcting the reconstruction. We propose SRD-guided Reconstruction Refinement (SRD-RR), which predicts a latent correction from a short SRD with the AE frozen and no per-sample test-time optimization. We also introduce MSE-recov, an MSE recovery ratio relative to an empirical decoder-optimized reference. Across six datasets, SRD-RR recovers 38.6% of the empirically recoverable MSE gap with one transition and 45.3% with two. A two-transition variant trained without direct access to original images, using an SRD-derived pseudo-target, achieves 40.7% recovery and a 1.74 dB average PSNR gain. Removing trajectory information reduces the gain, while cross-sample trajectory assignment causes severe degradation, confirming strong sample specificity. Nonlinear SRD-conditioned refinement consistently outperforms fixed and trained linear latent correction. On a pretrained DINOv2-based representation autoencoder (RAE) with substantially different latent dynamics, SRD conditioning again improves a matched trajectory-free predictor. However, pixel-MSE latent refinement reveals a strong mismatch between pixel fidelity and perceptual quality, while the SRD-derived pseudo-target mitigates this degradation. Overall, SRD is a useful sample-specific refinement signal, while the objective determines how it translates into pixel and perceptual quality.
Sep 17, 2026

Sharp Reconstruction Bounds for Autoencoders Using the Same Forward Map

We study reconstruction in autoencoders that apply the same forward map before and after setting the observed coordinates to zero. For equal odd input and hidden dimensions d≥3d\geq 3, among orientation-preserving diffeomorphisms whose Jacobian singular values lie in [m,M][m,M], we show that the least uniform reconstruction-derivative error is max⁡{1−M(M−m)/2,0}\max\{1-M(M-m)/2,0\}, with affine maps attaining this sharp bound at every prescribed depth. A translated radial rotation can nevertheless reconstruct any prescribed ball exactly with singular values arbitrarily close to one, motivating additional conditions for a finite-data bound. We test this prediction on a 798,452-point terrestrial LiDAR forest scan. At input scale 0.050.05, the mean theoretical bound is 0.1550.155, about 84%84\% of the mean normalized training error 0.1850.185 across four spatial regions, two depths, and three seeds. At this scale, adding one hidden coordinate reduces the mean reconstruction error below 6×10−66\times10^{-6}.
Sep 1, 2026

Superposed Latent Autoencoder

Autoencoders typically meet tight latent-memory budgets by making each latent representation smaller, sacrificing representational capacity. We ask a different question: can multiple wider latents be stored together instead? We introduce the Superposed Latent Autoencoder (SLAE), which preserves high-capacity latent representations while sharing storage through learned superposition. SLAE transforms latents into storage-friendly codes, binds them with randomized keys, superposes multiple codes into a single memory tensor, and learns to recover each latent before decoding. Under the same storage budget, SLAE replaces irreversible dimensional bottlenecks with structured interference that can be suppressed. Across CIFAR-10/100, SVHN, STL-10, Tiny ImageNet, and a wide range of memory budgets, SLAE substantially improves the reconstruction--memory tradeoff, reducing reconstruction error by up to 56% over conventional autoencoders at matched storage. Further analysis shows that SLAE's advantage comes from making wider representations usable under the same storage budget. These gains also extend beyond reconstruction: the information preserved by SLAE improves downstream classification by up to 16.79 percentage points under the same memory budget. Our results suggest a new principle for representation compression: instead of making every latent smaller, keep representations wide and let them share memory.