Score the Algebra, Not the Span: Dimension Reduction for Transfer Operator Models of Dynamical Systems

• URL: http://arxiv.org/abs/2608.18918v1
• Date: Wed, 19 Aug 2026 13:49:51 GMT
• Title: Score the Algebra, Not the Span: Dimension Reduction for Transfer Operator Models of Dynamical Systems
• Abstract summary: We show that on systems assembled from weakly interacting components, the component is absent from the model rather than modeled, and no function of it can be predicted at any accuracy.<n>We propose to score instead the $$-algebra the coordinates generate, so that products and powers come free and a component's cost is governed only by its generators.
• Score: 48.096969031315744
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Dimension reduction for dynamical systems is standard practice, and the standard route is spectral: model the transfer (Koopman) operator by its leading modes. We show that on systems assembled from several weakly interacting components --- a structure common in physical and biological settings --- this may either require an exponential number of modes, or drop an entire component: the component is absent from the model rather than modeled coarsely, and no function of it can be predicted at any accuracy. We call this linear masking. The cause is that a rank-based model pays one coordinate per mode. We propose to score instead the $σ$-algebra the coordinates generate, so that products and powers come free and a component's cost is governed only by its generators rather than by all its interactions. The criterion is a $χ^2$-divergence between the embedded present and future, and it carries a budget guarantee: twice the intrinsic dimension of the dynamics is enough coordinates for an embedding whose algebra carries the operator's entire spectrum, with its full infinite rank. In variational form the criterion admits off-the-shelf estimators, and restricting its critic to the bilinear class returns the VAMP score on the span, so rank-based methods are one end of the same family. We demonstrate the proposed objective on a composite of published benchmark systems. We exhibit examples where the rank-based methods completely miss the masked components at all ranks $k<100$, while ten algebra coordinates recover all of them. In addition, the resulting algebra representation supports predicting the masked components from few labels, while direct regression from the high-dimensional observation or from the VAMP features fail.

Related papers

• Neural Quadratic Forms: A Unified Minimal Model for Sudden Learning and Scaling Laws [12.27037893891717]
  Neural networks trained by gradient descent on a smooth cost function can learn in steps.<n>Training losses instead follow smooth power laws.<n>We show that a symmetry fixes what those variables are.
  arXiv  Detail & Related papers  (2026-08-13T15:05:43Z)
• Entangling Topological Invariants [1.5899159309486681]
  Isolated occupied multiplet may admit local tensor-product descriptions without a globally consistent subsystem structure.<n>We characterize the obstruction by comparing the transition functions of the occupied multiplet with those generated by independent basis changes in the two candidate subsystems.
  arXiv  Detail & Related papers  (2026-08-04T13:18:58Z)
• LegoQ: Density-Matrix Representation Learning with Spectral-Spatial State Transitions for Hyperspectral Classification [39.58966970890936]
  This paper presents method, a classical density-matrix representation learning framework for hyperspectral images.<n>The spectral bands are divided into groups and each group is mapped to a positive semi-definite, Hermitian, trace-normalized matrix state.<n>A composable stack of spectral, spatial, and inter-group transitions then updates the states while repeatedly projecting them back to the valid state set.<n>The results support constrained matrix-state learning as a practical alternative to vector-only hyperspectral classification without requiring quantum hardware.
  arXiv  Detail & Related papers  (2026-07-31T02:47:16Z)
• Inverting the Bellman Equation: From $Q$-Values to World Models [57.827849584133425]
  We prove that value-based agents trained on a sufficiently rich set of reward functions implicitly encode a unique and accurate world model.<n>We find that policies trained exclusively on a ttReacher agent's implicit world model are quasi-optimal on out-of-distribution, velocity-based goals despite position-only training.
  arXiv  Detail & Related papers  (2026-06-19T07:26:14Z)
• LoMETab: Beyond Rank-1 Ensembles for Tabular Deep Learning [0.2999888908665658]
  We propose LoMETab, a rank-$r$ generalization of multiplicative implicit ensembles.<n>LoMETab lifts the rank-1 BatchEnsemble/TabM modulation to a rank-$r$ identity-residual Hadamard family.<n> Empirically, we show that this added capacity manifests as measurable predictive diversity after training.
  arXiv  Detail & Related papers  (2026-05-14T04:47:16Z)
• S2MAM: Semi-supervised Meta Additive Model for Robust Estimation and Variable Selection [37.9993096742594]
  This paper proposes a new Semi-Supervised Meta Additive Model (S$2$MAM)<n>Based on a bilevel optimization scheme that automatically identifies informative variables, updates the similarity matrix, and simultaneously achieves interpretable predictions.<n> Experimental assessments across 4 synthetic and 12 real-world datasets, with varying levels and categories of corruption, validate the robustness and interpretability of the proposed approach.
  arXiv  Detail & Related papers  (2026-04-21T04:27:12Z)
• Phase-space entropy at acquisition reflects downstream learnability [54.4100065023873]
  We propose an acquisition-level scalar $S_mathcal B$ based on instrument-resolved phase space.<n>We show theoretically that (S_mathcal B) correctly identifies the phase-space coherence of periodic sampling.<n>$|S_mathcal B|$ consistently ranks sampling geometries and predicts downstream reconstruction/recognition difficulty emphwithout training.
  arXiv  Detail & Related papers  (2025-12-22T10:03:51Z)
• Benign Overfitting and the Geometry of the Ridge Regression Solution in Binary Classification [75.01389991485098]
  We show that ridge regression has qualitatively different behavior depending on the scale of the cluster mean vector.<n>In regimes where the scale is very large, the conditions that allow for benign overfitting turn out to be the same as those for the regression task.
  arXiv  Detail & Related papers  (2025-03-11T01:45:42Z)
• Transformers meet Stochastic Block Models: Attention with Data-Adaptive Sparsity and Cost [53.746169882193456]
  Recent works have proposed various sparse attention modules to overcome the quadratic cost of self-attention. We propose a model that resolves both problems by endowing each attention head with a mixed-membership Block Model. Our model outperforms previous efficient variants as well as the original Transformer with full attention.
  arXiv  Detail & Related papers  (2022-10-27T15:30:52Z)
• Frame Averaging for Invariant and Equivariant Network Design [50.87023773850824]
  We introduce Frame Averaging (FA), a framework for adapting known (backbone) architectures to become invariant or equivariant to new symmetry types. We show that FA-based models have maximal expressive power in a broad setting. We propose a new class of universal Graph Neural Networks (GNNs), universal Euclidean motion invariant point cloud networks, and Euclidean motion invariant Message Passing (MP) GNNs.
  arXiv  Detail & Related papers  (2021-10-07T11:05:23Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.