Search Results for author:
Found 47 papers, 19 papers with code
Membership Testing in Markov Equivalence Classes via Independence Query Oracles
While learning involves the task of recovering the Markov equivalence class (MEC) of the underlying causal graph from observational data, the testing counterpart addresses the following critical question: Given a specific MEC and observational data from some causal graph, can we determine if the data-generating causal graph belongs to the given MEC?
Causal Imputation for Counterfactual SCMs: Bridging Graphs and Latent Factor Models
We study the index-only setting, where the actions and contexts are categorical variables with a finite number of possible values.
Causal Discovery under Off-Target Interventions
Causal graph discovery is a significant problem with applications across various disciplines.
Removing Biases from Molecular Representations via Information Maximization
High-throughput drug screening -- using cell imaging or gene expression measurements as readouts of drug effect -- is a critical tool in biotechnology to assess and understand the relationship between the chemical structure and biological activity of a drug.
Meek Separators and Their Applications in Targeted Causal Discovery
In our work, we focus on two such well-motivated problems: subset search and causal matching.
Identifiability Guarantees for Causal Disentanglement from Soft Interventions
Causal disentanglement aims to uncover a representation of data using latent variables that are interrelated through a causal model.
Unsupervised Protein-Ligand Binding Energy Prediction via Neural Euler's Rotation Equation
Specifically, we train an energy-based model on a set of unlabelled protein-ligand complexes using SE(3) denoising score matching and interpret its log-likelihood as binding affinity.
Linear Causal Disentanglement via Interventions
A representation is identifiable if both the latent model and the transformation from latent to observed variables are unique.
Transfer Learning with Kernel Methods
In this work, we propose a transfer learning framework for kernel methods by projecting and translating the source model to the target task.
Active Learning for Optimal Intervention Design in Causal Models
Here, we develop a causal active learning strategy to identify interventions that are optimal, as measured by the discrepancy between the post-interventional mean of the distribution and a desired target mean.
Causal Structure Learning: a Combinatorial Perspective
In this review, we discuss approaches for learning causal structure from data, also called causal discovery.
Wide and Deep Neural Networks Achieve Optimality for Classification
In this work, we identify and construct an explicit set of neural network classifiers that achieve optimality.
Local Quadratic Convergence of Stochastic Gradient Descent with Adaptive Step Size
Establishing a fast rate of convergence for optimization methods is crucial to their applicability in practice.
Simple, Fast, and Flexible Framework for Matrix Completion with Infinite Width Neural Networks
Remarkably, taking the width of a neural network to infinity allows for improved computational performance.
Matching a Desired Causal State via Shift Interventions
In particular, we show that our strategies may require exponentially fewer interventions than the previously considered approaches, which optimize for structure learning in the underlying causal graph.
A Mechanism for Producing Aligned Latent Spaces with Autoencoders
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 tasks such as unsupervised clustering and data imputation.
Mol2Image: Improved Conditional Flow Models for Molecule to Image Synthesis
In this paper, we aim to synthesize cell microscopy images under different molecular interventions, motivated by practical applications to drug development.
Near-Optimal Multi-Perturbation Experimental Design for Causal Structure Learning
Causal structure learning is a key problem in many domains.
Identifying 3D Genome Organization in Diploid Organisms via Euclidean Distance Geometry
A standard approach is to transform the contact frequencies into noisy distance measurements and then apply semidefinite programming (SDP) formulations to obtain the 3D configuration.
LLBoost: Last Layer Perturbation to Boost Pre-trained Neural Networks
While deep networks have produced state-of-the-art results in several domains from image classification to machine translation, hyper-parameter selection remains a significant computational bottleneck.
Efficient Permutation Discovery in Causal DAGs
We compare our method with $w = 1$ to algorithms for finding sparse elimination orderings of undirected graphs, and show that taking advantage of DAG-specific problem structure leads to a significant improvement in the discovered permutation.
Increasing Depth Leads to U-Shaped Test Risk in Over-parameterized Convolutional Networks
We then present a novel linear regression framework for characterizing the impact of depth on test risk, and show that increasing depth leads to a U-shaped test risk for the linear CNTK.
Joint Inference of Multiple Graphs from Matrix Polynomials
Inferring graph structure from observations on the nodes is an important and popular network science task.
Do Deeper Convolutional Networks Perform Better?
Recent work provided an explanation for this phenomenon by introducing the double descent curve, showing that increasing model capacity past the interpolation threshold leads to a decrease in test error.
Linear Convergence and Implicit Regularization of Generalized Mirror Descent with Time-Dependent Mirrors
The following questions are fundamental to understanding the properties of over-parameterization in modern machine learning: (1) Under what conditions and at what rate does training converge to a global minimum?
Linear Convergence of Generalized Mirror Descent with Time-Dependent Mirrors
GMD subsumes popular first order optimization methods including gradient descent, mirror descent, and preconditioned gradient descent methods such as Adagrad.
Optimal Transport using GANs for Lineage Tracing
In this paper, we present Super-OT, a novel approach to computational lineage tracing that combines a supervised learning framework with optimal transport based on Generative Adversarial Networks (GANs).
Multiscale Simulations of Complex Systems by Learning their Effective Dynamics
Here we present a novel systematic framework that bridges large scale simulations and reduced order models to Learn the Effective Dynamics (LED) of diverse complex systems.
Improved Conditional Flow Models for Molecule to Image Synthesis
In this paper, we aim to synthesize cell microscopy images under different molecular interventions, motivated by practical applications to drug development.
On Alignment in Deep Linear Neural Networks
We define alignment for fully connected networks with multidimensional outputs and show that it is a natural extension of alignment in networks with 1-dimensional outputs as defined by Ji and Telgarsky, 2018.
Causal Structure Discovery from Distributions Arising from Mixtures of DAGs
We consider distributions arising from a mixture of causal models, where each model is represented by a directed acyclic graph (DAG).
Ordering-Based Causal Structure Learning in the Presence of Latent Variables
We consider the task of learning a causal graph in the presence of latent confounders given i. i. d.~samples from the model.
Overparameterized Neural Networks Implement Associative Memory
Identifying computational mechanisms for memorization and retrieval of data is a long-standing problem at the intersection of machine learning and neuroscience.
Overparameterized Neural Networks Can Implement Associative Memory
Identifying computational mechanisms for memorization and retrieval is a long-standing problem at the intersection of machine learning and neuroscience.
Downsampling leads to Image Memorization in Convolutional Autoencoders
In this paper, we link memorization of images in deep convolutional autoencoders to downsampling through strided convolution.
Size of Interventional Markov Equivalence Classes in Random DAG Models
For constant density, we show that the expected $\log$ observational MEC size asymptotically (in the number of vertices) approaches a constant.
ABCD-Strategy: Budgeted Experimental Design for Targeted Causal Structure Discovery
Determining the causal structure of a set of variables is critical for both scientific inquiry and decision-making.
Methodology
Multi-Domain Translation by Learning Uncoupled Autoencoders
Multi-domain translation seeks to learn a probabilistic coupling between marginal distributions that reflects the correspondence between different domains.
Scalable Unbalanced Optimal Transport using Generative Adversarial Networks
Generative adversarial networks (GANs) are an expressive class of neural generative models with tremendous success in modeling high-dimensional continuous measures.
Memorization in Overparameterized Autoencoders
The ability of deep neural networks to generalize well in the overparameterized regime has become a subject of significant research interest.
Characterizing and Learning Equivalence Classes of Causal DAGs under Interventions
We consider the problem of learning causal DAGs in the setting where both observational and interventional data is available.
Minimal I-MAP MCMC for Scalable Structure Discovery in Causal DAG Models
Learning a Bayesian network (BN) from data can be useful for decision-making or discovering causal relationships.
Direct Estimation of Differences in Causal Graphs
We consider the problem of estimating the differences between two causal directed acyclic graph (DAG) models given i. i. d.~samples from each model.
Methodology
Permutation-based Causal Inference Algorithms with Interventions
Learning directed acyclic graphs using both observational and interventional data is now a fundamentally important problem due to recent technological developments in genomics that generate such single-cell gene expression data at a very large scale.
Patchnet: Interpretable Neural Networks for Image Classification
Understanding how a complex machine learning model makes a classification decision is essential for its acceptance in sensitive areas such as health care.
Differentially-Private Logistic Regression for Detecting Multiple-SNP Association in GWAS Databases
Following the publication of an attack on genome-wide association studies (GWAS) data proposed by Homer et al., considerable attention has been given to developing methods for releasing GWAS data in a privacy-preserving way.
Learning directed acyclic graphs based on sparsest permutations
However, there is only limited work on consistency guarantees for score-based and hybrid algorithms and it has been unclear whether consistency guarantees can be proven under weaker conditions than the faithfulness assumption.
