Learning Temporally Causal Latent Processes from General Temporal Data
Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:NPZ54NMTrecord.jsonopen to challenge →
read the original abstract
Our goal is to recover time-delayed latent causal variables and identify their relations from measured temporal data. Estimating causally-related latent variables from observations is particularly challenging as the latent variables are not uniquely recoverable in the most general case. In this work, we consider both a nonparametric, nonstationary setting and a parametric setting for the latent processes and propose two provable conditions under which temporally causal latent processes can be identified from their nonlinear mixtures. We propose LEAP, a theoretically-grounded framework that extends Variational AutoEncoders (VAEs) by enforcing our conditions through proper constraints in causal process prior. Experimental results on various datasets demonstrate that temporally causal latent processes are reliably identified from observed variables under different dependency structures and that our approach considerably outperforms baselines that do not properly leverage history or nonstationarity information. This demonstrates that using temporal information to learn latent processes from their invertible nonlinear mixtures in an unsupervised manner, for which we believe our work is one of the first, seems promising even without sparsity or minimality assumptions.
This paper has not been read by Pith yet.
Forward citations
Cited by 7 Pith papers
-
From Generalist to Specialist Representation
Task structure is identifiable across time steps and task-relevant representations are identifiable within steps in a nonparametric setting under sparsity regularization.
-
Learning Individual Dynamics from Sparse Cross-Sectional Snapshots
CADENCE recovers individualized continuous-time trajectories from cross-sectional snapshots via context-anchored latent dynamics, a bijective score-based encoder, and SMoE routing, with claimed identifiability guarant...
-
Diverse Dictionary Learning
Diverse dictionary learning identifies intersections, complements, and dependency structures of latent variables from data X = g(Z) up to indeterminacies, and full identifiability when structural diversity is sufficient.
-
Extracting Governing Equations from Latent Dynamics via Multi-View Contrastive Learning
DYSCO jointly recovers latent trajectories and governing equations from noisy observations via multi-view contrastive learning, with theoretical guarantees up to affine indeterminacy.
-
MOSAIC: Module Discovery via Sparse Additive Identifiable Causal Learning for Scientific Time Series
MOSAIC recovers identifiable latent variables and their sparse associated observations in scientific time series by combining temporal causal representation learning with support recovery through a sparse additive decoder.
-
Factored Causal Representation Learning for Robust Reward Modeling in RLHF
A factored causal representation learning method improves robustness of reward models in RLHF by isolating causal factors from biases like length and sycophancy using adversarial gradient reversal.
-
MoVA: Learning Asymmetric Dual Projections for Modular Long Video-Text Alignment
MoVA introduces modular asymmetric dual projections to handle temporal misalignment and semantic asymmetry in long video-text alignment.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.