161 citations · 1k across the 69 of their papers we have counts for
80 papers
Synthetic Potential Outcomes and Causal Mixture Identifiability
Bijan Mazaheri, Chandler Squires, Caroline Uhler
Heterogeneous data from multiple populations, sub-groups, or sources is often represented as a ``mixture model'' with a single latent class influencing all of the observed covariat…
Causal Imputation for Counterfactual SCMs: Bridging Graphs and Latent Factor Models
Alvaro Ribot, Chandler Squires, Caroline Uhler
We consider the task of causal imputation, where we aim to predict the outcomes of some set of actions across a wide range of possible contexts. As a running example, we consider p…
Identifiability Guarantees for Causal Disentanglement from Soft Interventions
Jiaqi Zhang, Chandler Squires, Kristjan Greenewald +3
Causal disentanglement aims to uncover a representation of data using latent variables that are interrelated through a causal model. Such a representation is identifiable if the la…
Positivity in Linear Gaussian Structural Equation Models
Asad Lodhia, Jan-Christian Hütter, Caroline Uhler +1
We study a notion of positivity of Gaussian directed acyclic graphical models corresponding to a non-negativity constraint on the coefficients of the associated structural equation…
Unpaired Multi-Domain Causal Representation Learning
Nils Sturma, Chandler Squires, Mathias Drton +1
The goal of causal representation learning is to find a representation of data that consists of causally related latent variables. We consider a setup where one has access to data…
Unsupervised Protein-Ligand Binding Energy Prediction via Neural Euler's Rotation Equation
Wengong Jin, Siranush Sarkizova, Xun Chen +2
Protein-ligand binding prediction is a fundamental problem in AI-driven drug discovery. Prior work focused on supervised learning methods using a large set of binding affinity data…
Linear Causal Disentanglement via Interventions
Chandler Squires, Anna Seigal, Salil Bhate +1
Causal disentanglement seeks a representation of data involving latent variables that relate to one another via a causal model. A representation is identifiable if both the latent…
Transfer Learning with Kernel Methods
Adityanarayanan Radhakrishnan, Max Ruiz Luyten, Neha Prasad +1
Transfer learning refers to the process of adapting a model trained on a source task to a target task. While kernel methods are conceptually and computationally simple machine lear…
Active Learning for Optimal Intervention Design in Causal Models
Jiaqi Zhang, Louis Cammarata, Chandler Squires +2
Sequential experimental design to discover interventions that achieve a desired outcome is a key problem in various domains including science, engineering and public policy. When t…
Causal Structure Discovery between Clusters of Nodes Induced by Latent Factors
Chandler Squires, Annie Yun, Eshaan Nichani +2
We consider the problem of learning the structure of a causal directed acyclic graph (DAG) model in the presence of latent variables. We define latent factor causal models (LFCMs)…
Causal Structure Learning: a Combinatorial Perspective
Chandler Squires, Caroline Uhler
In this review, we discuss approaches for learning causal structure from data, also called causal discovery. In particular, we focus on approaches for learning directed acyclic gra…
Wide and Deep Neural Networks Achieve Optimality for Classification
Adityanarayanan Radhakrishnan, Mikhail Belkin, Caroline Uhler
While neural networks are used for classification tasks across domains, a long-standing open problem in machine learning is determining whether neural networks trained using standa…
Local Quadratic Convergence of Stochastic Gradient Descent with Adaptive Step Size
Adityanarayanan Radhakrishnan, Mikhail Belkin, Caroline Uhler
Establishing a fast rate of convergence for optimization methods is crucial to their applicability in practice. With the increasing popularity of deep learning over the past decade…
Maximum Likelihood Estimation for Brownian Motion Tree Models Based on One Sample
Michael Truell, Jan-Christian Hütter, Chandler Squires +2
We study the problem of maximum likelihood estimation given one data sample () over Brownian Motion Tree Models (BMTMs), a class of Gaussian models on trees. BMTMs are often u…
Simple, Fast, and Flexible Framework for Matrix Completion with Infinite Width Neural Networks
Adityanarayanan Radhakrishnan, George Stefanakis, Mikhail Belkin +1
Matrix completion problems arise in many applications including recommendation systems, computer vision, and genomics. Increasingly larger neural networks have been successful in m…
Matching a Desired Causal State via Shift Interventions
Jiaqi Zhang, Chandler Squires, Caroline Uhler
Transforming a causal system from a given initial state to a desired target state is an important task permeating multiple fields including control theory, biology, and materials s…
A Mechanism for Producing Aligned Latent Spaces with Autoencoders
Saachi Jain, Adityanarayanan Radhakrishnan, Caroline Uhler
Aligned latent spaces, where meaningful semantic shifts in the input space correspond to a translation in the embedding space, play an important role in the success of downstream t…
Near-Optimal Multi-Perturbation Experimental Design for Causal Structure Learning
Scott Sussex, Andreas Krause, Caroline Uhler
Causal structure learning is a key problem in many domains. Causal structures can be learnt by performing experiments on the system of interest. We address the largely unexplored p…
The DeCAMFounder: Non-Linear Causal Discovery in the Presence of Hidden Variables
Raj Agrawal, Chandler Squires, Neha Prasad +1
Many real-world decision-making tasks require learning causal relationships between a set of variables. Traditional causal discovery methods, however, require that all variables ar…
Identifying 3D Genome Organization in Diploid Organisms via Euclidean Distance Geometry
Anastasiya Belyaeva, Kaie Kubjas, Lawrence J. Sun +1
The spatial organization of the DNA in the cell nucleus plays an important role for gene regulation, DNA replication, and genomic integrity. Through the development of chromosome c…
Efficient Permutation Discovery in Causal DAGs
Chandler Squires, Joshua Amaniampong, Caroline Uhler
The problem of learning a directed acyclic graph (DAG) up to Markov equivalence is equivalent to the problem of finding a permutation of the variables that induces the sparsest gra…
Causal Imputation via Synthetic Interventions
Chandler Squires, Dennis Shen, Anish Agarwal +2
Consider the problem of determining the effect of a compound on a specific cell type. To answer this question, researchers traditionally need to run an experiment applying the drug…
Joint Inference of Multiple Graphs from Matrix Polynomials
Madeline Navarro, Yuhao Wang, Antonio G. Marques +2
Inferring graph structure from observations on the nodes is an important and popular network science task. Departing from the more common inference of a single graph and motivated…
Increasing Depth Leads to U-Shaped Test Risk in Over-parameterized Convolutional Networks
Eshaan Nichani, Adityanarayanan Radhakrishnan, Caroline Uhler
Recent works have demonstrated that increasing model capacity through width in over-parameterized neural networks leads to a decrease in test risk. For neural networks, however, mo…