activity
20242026
collaborators
Showing stat.MLShow all

7 papers · 1 filter

stat.ML2026

Intervening to Learn and Compose Causally Disentangled Representations

Alex Markham, Isaac Hirsch, Jeri A. Chang +2

In designing generative models, it is commonly believed that in order to learn useful latent structure, we face a fundamental tension between expressivity and structure. In this pa…

stat.ML2026

Beyond identifiability: Learning causal representations with few environments and finite samples

Inbeom Lee, Tongtong Jin, Bryon Aragam

We provide explicit, finite-sample guarantees for learning causal representations from data with a sublinear number of environments. Causal representation learning seeks to provide…

stat.ML2026

Towards Interpretable Deep Generative Models via Causal Representation Learning

Gemma E. Moran, Bryon Aragam

Recent developments in generative artificial intelligence (AI) rely on machine learning techniques such as deep learning and generative modeling to achieve state-of-the-art perform…

stat.ML2024

Markov Equivalence and Consistency in Differentiable Structure Learning

Chang Deng, Kevin Bello, Pradeep Ravikumar +1

Existing approaches to differentiable structure learning of directed acyclic graphs (DAGs) rely on strong identifiability assumptions in order to guarantee that global minimizers o…

stat.ML2024

Dimension-independent rates for structured neural density estimation

Robert A. Vandermeulen, Wai Ming Tai, Bryon Aragam

We show that deep neural networks achieve dimension-independent rates of convergence for learning structured densities such as those arising in image, audio, video, and text applic…

stat.ML2024

Breaking the curse of dimensionality in structured density estimation

Robert A. Vandermeulen, Wai Ming Tai, Bryon Aragam

We consider the problem of estimating a structured multivariate density, subject to Markov conditions implied by an undirected graph. In the worst case, without Markovian assumptio…