conftrace_

identifiability theory

9 papers

Explore in graph

Co-occurring keywords · papers mentioning both

representation learning (3) t-process prior (1) causal graphical model (1) causal representation (1) infonce loss (1) temporal context (1) synthetic benchmark (1) partial disentanglement (1) data generating process (1) mechanism sparsity (1)

Papers

Nonparametric Partial Disentanglement via Mechanism Sparsity: Sparse Actions, Interventions and Sparse Temporal Dependencies JMLR 2026 Partially Observed Structural Causal Models UAI 2026 Who Guards the Guardians? The Challenges of Evaluating Identifiability of Learned Representations UAI 2026 All or None: Identifiable Linear Properties of Next-Token Predictors in Language Modeling AISTATS 2025 InfoNCE: Identifying the Gap Between Theory and Practice AISTATS 2025 Position: An Empirically Grounded Identifiability Theory Will Accelerate Self Supervised Learning Research ICML 2025 CaRiNG: Learning Temporal Causal Representation under Non-Invertible Generation Process ICML 2024 Identifiable Feature Learning for Spatial Data with Nonlinear ICA AISTATS 2024 Provable Compositional Generalization for Object-Centric Learning ICLR 2024