Bryon Aragam

Intervening to learn and compose causally disentangled representations CLeaR 2026 Learning general conditional independence structures via the neighbourhood lattice JMLR 2026 Dimension-Independent Rates for Structured Neural Density Estimation ICML 2025 Breaking the curse of dimensionality in structured density estimation NeurIPS 2024 Do LLMs dream of elephants (when told not to)? Latent concept association and associative memory in transformers NeurIPS 2024 From Causal to Concept-Based Representation Learning NeurIPS 2024 Identifying General Mechanism Shifts in Linear Causal Representations NeurIPS 2024 Inconsistency of Cross-Validation for Structure Learning in Gaussian Graphical Models AISTATS 2024 Markov Equivalence and Consistency in Differentiable Structure Learning NeurIPS 2024 On the Origins of Linear Representations in Large Language Models ICML 2024 Optimal estimation of Gaussian (poly)trees AISTATS 2024 Assumption violations in causal discovery and the robustness of score matching NeurIPS 2023 Global Optimality in Bivariate Gradient-based DAG Learning NeurIPS 2023 iSCAN: Identifying Causal Mechanism Shifts among Nonlinear Additive Noise Models NeurIPS 2023 Learning Linear Causal Representations from Interventions under General Nonlinear Mixing NeurIPS 2023 Learning Mixtures of Gaussians with Censored Data ICML 2023 Learning Nonparametric Latent Causal Graphs with Unknown Interventions NeurIPS 2023 Optimizing NOTEARS Objectives via Topological Swaps ICML 2023 Tight Bounds on the Hardness of Learning Simple Nonparametric Mixtures COLT 2023 Uncovering Meanings of Embeddings via Partial Orthogonality NeurIPS 2023 DAGMA: Learning DAGs via M-matrices and a Log-Determinant Acyclicity Characterization NeurIPS 2022 Fundamental Limits and Tradeoffs in Invariant Representation Learning JMLR 2022 Identifiability of deep generative models without auxiliary information NeurIPS 2022 On perfectness in Gaussian graphical models AISTATS 2022 Optimal estimation of Gaussian DAG models AISTATS 2022 Efficient Bayesian network structure learning via local Markov boundary search NeurIPS 2021 Learning latent causal graphs via mixture oracles NeurIPS 2021 Structure learning in polynomial time: Greedy algorithms, Bregman information, and exponential families NeurIPS 2021 A polynomial-time algorithm for learning nonparametric causal graphs NeurIPS 2020 Automated Dependence Plots UAI 2020 DYNOTEARS: Structure Learning from Time-Series Data AISTATS 2020 Learning Sparse Nonparametric DAGs AISTATS 2020 Fault Tolerance in Iterative-Convergent Machine Learning ICML 2019 Globally optimal score-based learning of directed acyclic graphs in high-dimensions NeurIPS 2019 Learning Sample-Specific Models with Low-Rank Personalized Regression NeurIPS 2019 DAGs with NO TEARS: Continuous Optimization for Structure Learning NeurIPS 2018 The Sample Complexity of Semi-Supervised Learning with Nonparametric Mixture Models NeurIPS 2018 Concave Penalized Estimation of Sparse Gaussian Bayesian Networks JMLR 2015