Papers for

industrial sensor engineers

Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.

Test-time optimization improves missing channel recovery in time series

From Reconstruction to Imputation: Test-Time Optimization for Missing Time-Series Channels

Abstract: Complete sensor-channel failures create a difficult form of time-series missingness: local interpolation is unavailable, and deploying a separately trained imputer for every failure pattern may be impractical. We ask whether a sequence reconstructor trained without artificial mask augmentation and then frozen can be converted into an imputer at inference time. Our method treats the missing entries of each test window as optimization variables, clamps all observations, and backpropagates through the frozen model to minimize reconstruction error only on observed coordinates. The resulting observed-self-consistency objective requires neither artificial mask augmentation nor full-channel dropout during reconstructor training. We characterize when this refinement is informative through the cross-Jacobian from missing inputs to observed residuals, and use an optional temporal-smoothness prior when that coupling is weak. Across five real-world datasets with exactly one channel synthetically masked per test window and four reconstruction architectures, no-prior test-time refinement reduces MAE relative to one-pass reconstruction in 19 of 20 dataset-backbone combinations. Compared with mask-aware imputers trained under either standard structured masks or matched full-channel dropout, the best refined reconstructor achieves the lowest MAE on two datasets and trails the strongest baseline on three. These gains require substantially more inference time and are sensitive to cross-channel coupling. Our results establish test-time self-consistency as a conditional inference-time adapter for frozen reconstruction models that complements mask-aware imputation without retraining the reconstructor.

Wed 4 NovMachine LearningArtificial Intelligence
The gist
Time-series data from sensors often lose entire channels, making it hard to fill in gaps using common methods. The authors show you can take a model trained to reconstruct sequences and, without retraining, optimize the unknown missing values at test time to better match the observed data. This approach works well on several real datasets and different model types, especially when the missing data strongly affects the observed data. It is slower than standard methods but can improve accuracy without needing extra training for each failure pattern.
Open → 2611.06612v1

Multi-domain approach identifies linked hidden factors from mixed signals

Identifying Dependent Components from Multi-domain Linear Mixtures

Abstract: We study a linear mixing model with dependent latent components, assuming multiple data domains. Most existing models assume that the components are independent or at least uncorrelated, in line with independent component analysis (ICA). Some recent work allows for dependent components, but then makes specific assumptions such as parametric forms of dependencies, multi-view settings, or interventions, or does not recover the individual components. In contrast, we consider a multi-domain setting in which domains differ through domain-specific scalings of the components, while the distribution of the underlying latent components is the same across domains. This approach can model data collected, for example, from different sensors measuring the same process, different laboratories conducting the same experiment, different experimental conditions, or different subjects that might differ in biological or physiological factors. We show that, under sufficient domain variability, latent variables and mixing functions can be identified from second-order statistics alone. We propose the Multi-Domain Covariance Matching (MuDo-CoM) algorithm that generalizes previous methods of joint diagonalization. MuDo-CoM is validated on simulated data and a real-world fMRI dataset.

Tue 20 OctMachine LearningArtificial Intelligence
The gist
When you have data from different sources measuring the same thing, the hidden factors they measure can be tangled up and related. Most techniques assume these hidden factors act independently, but the authors study a way to uncover linked hidden factors across different data sources. They do this by looking at how the variation changes across sources rather than assuming independence. Their method, MuDo-CoM, uses these differences to successfully find both the hidden factors and how they mix to form the observed data.
Open → 2610.28330v1

Neural networks uncover hidden frequency patterns in time series data

Inverse Cross-spectral Neural Networks for Multivariate Time Series

Abstract: CoVariance Neural Networks and their extensions have emerged as effective tools for processing multivariate data, deriving graph shift operators directly from second-order statistics. These architectures, however, are designed for independent and identically distributed observations and do not fully capture the joint structure of temporal and cross-variable dependencies in multivariate time series. In this work, we introduce Inverse Cross-Spectral Neural Networks (iCSNNs), a class of graph neural networks for stationary multivariate time series whose shift operators are the inverse cross-spectral density (iCSD) matrices. These operators encode frequency-specific conditional relationships among variables, exploiting the decomposition provided by the spectral representation theorem. Leveraging spectral smoothness, frequencies are grouped into bands sharing a single iCSD operator, yielding a compact parametrisation that retains the frequency-dependent structure of the process. We further propose a joint learning procedure to estimate both the Fourier-domain dependence structure and the iCSNN parameters, adapting the iCSD operators to the downstream task. When tested on synthetic data, iCSNN outperforms baselines from different methodological families.

Mon 5 OctMachine Learning
The gist
Analyzing data with many variables changing over time is tricky because these variables influence each other differently at different frequencies. The authors present a new type of neural network that looks at these frequency-specific relationships to better understand how variables connect and change together over time. Their method groups similar frequencies to simplify the model while keeping important details. Tests with made-up data show their approach predicts these complex relationships more accurately than other methods.
Open → 2610.06630v1

Machines find the hidden language of physical measurements

Discovering Physical Representation Languages

Abstract: Before a machine can discover a physical law, it must discover what its measurements are: which observations live on cells, which are intensive or extensive, which sectors are dual, and which distinctions are merely gauge. We introduce physical representation-language discovery, the problem of recovering this hidden ontology directly from anonymous controlled experiments. We give an identifiability theory and constructive polynomial-time procedure that recovers a carrier and differential sequence, measurement types and orientation twist, noninvertible refinement semantics, primal-dual Maxwell diagrams, and the residual equivalences that no permitted experiment can break. The theory turns material nuisance into a commutant, uses refinement to separate quantities from coordinates, and selects physics only after its representation has been recovered. For a certified finite experiment family, we prove an end-to-end two-stage measurement bound and a matching minimax rate in dimension, accuracy, and confidence. Blind Maxwell experiments recover complete primal/relative-dual ontologies on regular and unstructured carriers under jointly corrupted observations; an independent unstructured RLC system demonstrates that the result is not specific to Maxwell. The framework scales to tens of thousands of cells per carrier, while stress audits demonstrate robustness across severe physical regimes - including non-Markovian memory, nonlinearities, nonlocality, and complex constitutive hysteresis. A public FDTD audit demonstrates the emergence of anonymous curl structure from incomplete field data, while characterizing the informational prerequisites for complete recovery. The goal is to move scientific ML from learning laws in a human-supplied language to discovering the language in which laws become expressible, establishing exact theoretical limits on observational identifiability.

Sun 20 SeptMachine LearningArtificial Intelligence
The gist
Before machines can find physical laws, they need to understand what their measurement data actually represent. The authors develop a method that helps machines discover this hidden measurement language just by looking at controlled experiments, without prior knowledge. Their method works efficiently and can handle complicated situations, even when the data is noisy or incomplete. This advances the ability of machines to learn physical laws in the languages where these laws naturally make sense rather than in human-made formulas.
Open → 2609.23381v1