
Optimization of Graph Neural Networks: Implicit Acceleration by Skip Connections and More Depth
Graph Neural Networks (GNNs) have been studied from the lens of expressi...
read it

Counting Substructures with HigherOrder Graph Neural Networks: Possibility and Impossibility Results
While massage passing based Graph Neural Networks (GNNs) have become inc...
read it

Contrastive Learning with Hard Negative Samples
We consider the question: how can you sample good negative examples for ...
read it

Graph Adversarial Networks: Protecting Information against Adversarial Attacks
We study the problem of protecting information when learning with graph ...
read it

How Neural Networks Extrapolate: From Feedforward to Graph Neural Networks
We study how neural networks trained by gradient descent extrapolate, i....
read it

Testing Determinantal Point Processes
Determinantal point processes (DPPs) are popular probabilistic models of...
read it

Estimating Generalization under Distribution Shifts via DomainInvariant Representations
When machine learning models are deployed on a test distribution differe...
read it

Debiased Contrastive Learning
A prominent technique for selfsupervised representation learning has be...
read it

IDEAL: Inexact DEcentralized Accelerated Augmented Lagrangian Method
We introduce a framework for designing primal methods under the decentra...
read it

Distributionally Robust Bayesian Optimization
Robustness to distributional shift is one of the key challenges of conte...
read it

Strength from Weakness: Fast Learning Using Weak Supervision
We study generalization properties of weakly supervised learning. That i...
read it

Generalization and Representational Limits of Graph Neural Networks
We address two fundamental questions about graph neural networks (GNNs)....
read it

On the Complexity of Minimizing Convex Finite Sums Without Using the Indices of the Individual Functions
Recent advances in randomized incremental methods for minimizing Lsmoot...
read it

Adaptive Sampling for Stochastic RiskAverse Learning
We consider the problem of training machine learning models in a riskav...
read it

The Role of Embedding Complexity in Domaininvariant Representations
Unsupervised domain adaptation aims to generalize the hypothesis trained...
read it

Flexible Modeling of Diversity with Strongly LogConcave Distributions
Strongly logconcave (SLC) distributions are a rich class of discrete pr...
read it

Are Girls Neko or Shōjo? CrossLingual Alignment of NonIsomorphic Embeddings with Iterative Normalization
Crosslingual word embeddings (CLWE) underlie many multilingual natural ...
read it

What Can Neural Networks Reason About?
Neural networks have successfully been applied to solving reasoning task...
read it

Minimizing approximately submodular functions
The problem of minimizing a submodular function is well studied; several...
read it

Distributionally Robust Optimization and Generalization in Kernel Methods
Distributionally robust optimization (DRO) has attracted attention in ma...
read it

Learning Generative Models across Incomparable Spaces
Generative Adversarial Networks have shown remarkable success in learnin...
read it

Inorganic Materials Synthesis Planning with LiteratureTrained Neural Networks
Leveraging new data sources is a key step in accelerating the pace of ma...
read it

Adversarially Robust Optimization with Gaussian Processes
In this paper, we consider the problem of Gaussian process (GP) optimiza...
read it

How Powerful are Graph Neural Networks?
Graph Neural Networks (GNNs) for representation learning of graphs broad...
read it

Discrete Sampling using Semigradientbased Product Mixtures
We consider the problem of inference in discrete probabilistic models, t...
read it

ResNet with oneneuron hidden layers is a Universal Approximator
We demonstrate that a very deep ResNet with stacked modules with one neu...
read it

Towards Optimal Transport with Global Invariances
Many problems in machine learning involve calculating correspondences be...
read it

Representation Learning on Graphs with Jumping Knowledge Networks
Recent deep learning approaches for representation learning on graphs fo...
read it

Robust GANs against Dishonest Adversaries
Robustness of deep learning models is a property that has recently gaine...
read it

Distributionally Robust Submodular Maximization
Submodular functions have applications throughout machine learning, but ...
read it

Structured Optimal Transport
Optimal Transport has recently gained interest in machine learning for a...
read it

GraphSparse Logistic Regression
We introduce GraphSparse Logistic Regression, a new algorithm for class...
read it

Ensemble Bayesian Optimization
Bayesian Optimization (BO) has been shown to be a very effective paradig...
read it

Parallel Streaming Wasserstein Barycenters
Efficiently aggregating data from different sources is a challenging pro...
read it

Polynomial Time Algorithms for Dual Volume Sampling
We study dual volume sampling, a method for selecting k columns from an ...
read it

Batched Highdimensional Bayesian Optimization via Structural Kernel Learning
Optimization of highdimensional blackbox functions is an extremely cha...
read it

Maxvalue Entropy Search for Efficient Bayesian Optimization
Entropy Search (ES) and Predictive Entropy Search (PES) are popular and ...
read it

Robust Budget Allocation via Continuous Submodular Functions
The optimal allocation of resources for maximizing influence, spread of ...
read it

Deep Metric Learning via Facility Location
Learning the representation and the similarity metric in an endtoend f...
read it

Fast Mixing Markov Chains for Strongly Rayleigh Measures, DPPs, and Constrained Sampling
We study probability measures induced by set functions with constraints....
read it

Focused ModelLearning and Planning for NonGaussian Continuous StateAction Systems
We introduce a framework for model learning and planning in stochastic d...
read it

Fast Sampling for Strongly Rayleigh Measures with Application to Determinantal Point Processes
In this note we consider sampling from (nonhomogeneous) strongly Raylei...
read it

Gauss quadrature for matrix inverse forms with applications
We present a framework for accelerating a spectrum of machine learning a...
read it

Optimization as Estimation with Gaussian Processes in Bandit Settings
Recently, there has been rising interest in Bayesian optimization  the...
read it

Convex Optimization for Parallel Energy Minimization
Energy minimization has been an intensely studied core problem in comput...
read it

Submodular meets Structured: Finding Diverse Subsets in ExponentiallyLarge Structured Item Sets
To cope with the high level of ambiguity faced in domains such as Comput...
read it

Weaklysupervised Discovery of Visual Pattern Configurations
The increasing prominence of weakly labeled data nurtures a growing dema...
read it

Graph Cuts with Interacting Edge Costs  Examples, Approximations, and Algorithms
We study an extension of the classical graph cut problem, wherein we rep...
read it

Optimistic Concurrency Control for Distributed Unsupervised Learning
Research on distributed machine learning algorithms has focused primaril...
read it
Stefanie Jegelka
is this you? claim profile
Assistant Professor at Massachusetts Institute of Technology (MIT)