216 citations · 454 across the 55 of their papers we have counts for
55 papers
Is This Your Final Answer? Cross-Contextual Consistency as a Measure of LLM Credibility
Siyang Wu, Yibo Jiang, Bryon Aragam
Large language models (LLMs) are powerful black-box systems, making it difficult to discern whether their answers reflect stable internal beliefs or superficial pattern matching. W…
CMB constraints on dark matter-proton scattering: investigating prior-volume effects using profile likelihoods
Maria C. Straight, Tanvi Karwal, José Luis Bernal +1
We present profile-likelihood constraints on velocity-independent dark matter-proton scattering, including cases in which only a fraction of dark matter has such non-gravitational…
Differentiable Structure Learning and Causal Discovery for General Binary Data
Chang Deng, Bryon Aragam
Existing methods for differentiable structure learning in discrete data typically assume that the data are generated from specific structural equation models. However, these assump…
Optimality and computational barriers in variable selection under dependence
Ming Gao, Bryon Aragam
We study the optimal sample complexity of variable selection in linear regression under general design covariance, and show that subset selection is optimal while under standard co…
Optimal structure learning and conditional independence testing
Ming Gao, Yuhao Wang, Bryon Aragam
We establish a fundamental connection between optimal structure learning and optimal conditional independence testing by showing that the minimax optimal rate for structure learnin…
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…
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…
ScoreFlow: Mastering LLM Agent Workflows via Score-based Preference Optimization
Yinjie Wang, Ling Yang, Guohao Li +2
Recent research has leveraged large language model multi-agent systems for complex problem-solving while trying to reduce the manual effort required to build them, driving the deve…
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…
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…
Identifying General Mechanism Shifts in Linear Causal Representations
Tianyu Chen, Kevin Bello, Francesco Locatello +2
We consider the linear causal representation learning setting where we observe a linear mixing of unknown latent factors, which follow a linear structural causal model. Recent…
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…
Model-free Estimation of Latent Structure via Multiscale Nonparametric Maximum Likelihood
Bryon Aragam, Ruiyi Yang
Multivariate distributions often carry latent structures that are difficult to identify and estimate, and which better reflect the data generating mechanism than extrinsic structur…
Greedy equivalence search for nonparametric graphical models
Bryon Aragam
One of the hallmark achievements of the theory of graphical models and Bayesian model selection is the celebrated greedy equivalence search (GES) algorithm due to Chickering and Me…
Do LLMs dream of elephants (when told not to)? Latent concept association and associative memory in transformers
Yibo Jiang, Goutham Rajendran, Pradeep Ravikumar +1
Large Language Models (LLMs) have the capacity to store and recall facts. Through experimentation with open-source models, we observe that this ability to retrieve facts can be eas…
On the Origins of Linear Representations in Large Language Models
Yibo Jiang, Goutham Rajendran, Pradeep Ravikumar +2
Recent works have argued that high-level semantic concepts are encoded "linearly" in the representation space of large language models. In this work, we study the origins of such l…
Optimal estimation of Gaussian (poly)trees
Yuhao Wang, Ming Gao, Wai Ming Tai +2
We develop optimal algorithms for learning undirected Gaussian trees and directed Gaussian polytrees from data. We consider both problems of distribution learning (i.e. in KL dista…
Learning Interpretable Concepts: Unifying Causal Representation Learning and Foundation Models
Goutham Rajendran, Simon Buchholz, Bryon Aragam +2
To build intelligent machine learning systems, there are two broad approaches. One approach is to build inherently interpretable models, as endeavored by the growing field of causa…
Inconsistency of cross-validation for structure learning in Gaussian graphical models
Zhao Lyu, Wai Ming Tai, Mladen Kolar +1
Despite numerous years of research into the merits and trade-offs of various model selection criteria, obtaining robust results that elucidate the behavior of cross-validation rema…
Uncovering Meanings of Embeddings via Partial Orthogonality
Yibo Jiang, Bryon Aragam, Victor Veitch
Machine learning tools often rely on embedding text as vectors of real numbers. In this paper, we study how the semantic structure of language is encoded in the algebraic structure…
Assumption violations in causal discovery and the robustness of score matching
Francesco Montagna, Atalanti A. Mastakouri, Elias Eulig +5
When domain knowledge is limited and experimentation is restricted by ethical, financial, or time constraints, practitioners turn to observational causal discovery methods to recov…
Global Optimality in Bivariate Gradient-based DAG Learning
Chang Deng, Kevin Bello, Bryon Aragam +1
Recently, a new class of non-convex optimization problems motivated by the statistical problem of learning an acyclic directed graphical model from data has attracted significant i…
Learning Mixtures of Gaussians with Censored Data
Wai Ming Tai, Bryon Aragam
We study the problem of learning mixtures of Gaussians with censored data. Statistical learning with censored data is a classical problem, with numerous practical applications, how…
iSCAN: Identifying Causal Mechanism Shifts among Nonlinear Additive Noise Models
Tianyu Chen, Kevin Bello, Bryon Aragam +1
Structural causal models (SCMs) are widely used in various disciplines to represent causal relationships among variables in complex systems. Unfortunately, the underlying causal st…