← 研踪 PaperTrailarXiv:2605.15995 · v4
Constrained latent state modeling: A unifying perspective on representation learning under competing constraints
首次提交 2026-05-15 22:25
版本更新 2026-11-16 23:33
雷达观测 2026-11-17 16:10
摘要
Learning latent representations from temporal, multimodal, and partially observed data requires specifying what information a latent state should retain, discard, and organize. Existing approaches encode these requirements through heterogeneous objectives, making methods difficult to compare and learned representations difficult to interpret. We propose Constrained Latent State Modeling (CLSM), a conceptual framework that characterizes latent states through six complementary properties: predictive sufficiency, minimality, temporal coherence, observation compatibility, invariance to nuisance factors, and structural constraints. CLSM separates these properties from the surrogate objectives used to induce them and from the diagnostics used to evaluate them, and clarifies how combinations of constraints can improve identifiability by restricting the space of admissible representations. We reinterpret major representation-learning families through this common design space and illustrate the framework with a controlled synthetic benchmark. The experiments show how objectives produce distinct latent organizations and empirical trade-offs depending on the prediction target, surrogate formulation, parameterization, and optimization. Companion repository containing the reference implementation, reproducible experiments, documentation, and model cards: https://github.com/gwenole-quellec/clsm
作者备注:Accepted for publication in Patterns (Cell Press). This is a metadata-only update. The PDF corresponds to an earlier version of the manuscript and does not incorporate the revisions made during subsequent rounds of peer review
观测到的版本
相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。
v5 · 2026-11-18 21:46 · 最新观测版本
What competing constraints reveal about representation learning
Learning latent states from temporal, multimodal, and partially observed data requires decisions about what information representations should retain, discard, and organize. I argue that six complementary properties help clarify these decisions: predictive sufficiency, minimality, temporal coherence, observation compatibility, nuisance invariance, and structural constraints. Drawing on established approaches, I distinguish desired representation properties from the objectives used to encourage them and the diagnostics used to assess them, since neither a training objective nor an evaluation metric guarantees that a property has been achieved. Controlled synthetic experiments examine how training objectives influence predictive performance, nuisance decodability, and latent organization. The results reveal discrepancies between seemingly favorable diagnostics and the information retained in learned representations, as well as latent-coordinate ambiguities under equivalent predictive performance, illustrating how complementary evaluations can improve interpretation and guide design choices. Together, these analyses provide a basis for designing, comparing, and evaluating learned latent states.
查看此版本解读 →查看此版本原文 ↗v4 · 2026-11-16 23:33
Constrained latent state modeling: A unifying perspective on representation learning under competing constraints
Learning latent representations from temporal, multimodal, and partially observed data requires specifying what information a latent state should retain, discard, and organize. Existing approaches encode these requirements through heterogeneous objectives, making methods difficult to compare and learned representations difficult to interpret. We propose Constrained Latent State Modeling (CLSM), a conceptual framework that characterizes latent states through six complementary properties: predictive sufficiency, minimality, temporal coherence, observation compatibility, invariance to nuisance factors, and structural constraints. CLSM separates these properties from the surrogate objectives used to induce them and from the diagnostics used to evaluate them, and clarifies how combinations of constraints can improve identifiability by restricting the space of admissible representations. We reinterpret major representation-learning families through this common design space and illustrate the framework with a controlled synthetic benchmark. The experiments show how objectives produce distinct latent organizations and empirical trade-offs depending on the prediction target, surrogate formulation, parameterization, and optimization. Companion repository containing the reference implementation, reproducible experiments, documentation, and model cards: https://github.com/gwenole-quellec/clsm
查看此版本解读 →查看此版本原文 ↗