Stefanie Jegelka

46

Papers

219

Total Citations

Papers (46)

Parallel Streaming Wasserstein Barycenters

NeurIPS 2017arXiv

Fast Mixing Markov Chains for Strongly Rayleigh Measures, DPPs, and Constrained Sampling

NeurIPS 2016arXiv

On the Emergence of Position Bias in Transformers

Polynomial time algorithms for dual volume sampling

NeurIPS 2017arXiv

On the hardness of learning under symmetries

Learning Diffusion Models with Flexible Representation Guidance

NeurIPS 2025arXiv

Beyond Interpretability: The Gains of Feature Monosemanticity on Model Robustness

Learning Linear Attention in Polynomial Time

Deep Metric Learning via Lifted Structured Feature Embedding

Cooperative Graphical Models

Robust Contrastive Learning Against Noisy Views

Simplicity Bias via Global Convergence of Sharpness Minimization

A Universal Class of Sharpness-Aware Minimization Algorithms

Sample Complexity Bounds for Estimating Probability Divergences under Invariances

Position: Future Directions in the Theory of Graph Machine Learning

Can Looped Transformers Learn to Implement Multi-step Gradient Descent for In-context Learning?

Geometric Algorithms for Neural Combinatorial Optimization with Constraints

NeurIPS 2025arXiv

Deep Metric Learning via Facility Location

Expressive Sign Equivariant Networks for Spectral Geometric Learning

What is the Inductive Bias of Flatness Regularization? A Study of Deep Matrix Factorization Models

Limits, approximation and size transferability for GNNs on sparse graphs via graphops

The Exact Sample Complexity Gain from Invariances for Kernel Regression

Gaussian quadrature for matrix inverse forms with applications

Fast DPP Sampling for Nystrom with Application to Kernel Methods

Robust Budget Allocation via Continuous Submodular Functions

Max-value Entropy Search for Efficient Bayesian Optimization

Batched High-dimensional Bayesian Optimization via Structural Kernel Learning

Representation Learning on Graphs with Jumping Knowledge Networks

Learning Generative Models across Incomparable Spaces

ResNet with one-neuron hidden layers is a Universal Approximator

Provable Variational Inference for Constrained Log-Submodular Models

Exponentiated Strongly Rayleigh Distributions

Adversarially Robust Optimization with Gaussian Processes

Distributionally Robust Optimization and Generalization in Kernel Methods

Flexible Modeling of Diversity with Strongly Log-Concave Distributions

Adaptive Sampling for Stochastic Risk-Averse Learning

Debiased Contrastive Learning

Testing Determinantal Point Processes

IDEAL: Inexact DEcentralized Accelerated Augmented Lagrangian Method

What training reveals about neural network complexity

Can contrastive learning avoid shortcut solutions?

Measuring Generalization with Optimal Transport

Scaling up Continuous-Time Markov Chains Helps Resolve Underspecification

Tree Mover's Distance: Bridging Graph Metrics and Stability of Graph Neural Networks

Neural Set Function Extensions: Learning with Discrete Functions in High Dimensions

On the generalization of learning algorithms that do not converge