Stefanie Jegelka
112 publications
10 venues
H Index 37
Affiliation
TU Munich, GermanyMassachusetts Institute of Technology (MIT), CSAIL, Cambridge, MA, USA
University of California, Berkeley, Department of EECS, Berkeley, CA, USA
ETH Zurich, Department of Computer Science, Switzerland
Max Planck Institute for Intelligent Systems, T bingen, Germany
University of T bingen, Wilhelm Schickard Institute for Computer Sciences, Germany
Links
DBLPGoogle Scholar
- https://people.csail.mit.edu/stefje/
- http://www.is.tuebingen.mpg.de/nc/employee/details/jegelka.html
- https://www.wikidata.org/entity/Q102683371
- https://en.wikipedia.org/wiki/Stefanie_Jegelka
- https://d-nb.info/gnd/1029803285
- https://mathgenealogy.org/id.php?id=218795
- https://dblp.uni-trier.de/pers/hd/j/Jegelka:Stefanie_Sabrina
| Name | Venue | Year | citations |
|---|---|---|---|
Regularity in Canonicalized Models: A Theoretical Perspective.
|
AISTATS | 2025 | 2 |
| On the Emergence of Position Bias in Transformers.
|
ICML | 2025 | 35 |
| A Robust Kernel Statistical Test of Invariance: Detecting Subtle Asymmetries.
|
AISTATS | 2025 | 1 |
| Generalization, Expressivity, and Universality of Graph Neural Networks on Attributed Graphs.
|
ICLR | 2025 | 0 |
| Generalization Bounds for Canonicalization: A Comparative Study with Group Averaging.
|
ICLR | 2025 | 5 |
| Beyond Matryoshka: Revisiting Sparse Coding for Adaptive Representation.
|
ICML | 2025 | 14 |
| Learning with Exact Invariances in Polynomial Time.
|
ICML | 2025 | 1 |
| Higher-Order Graphon Neural Networks: Approximation and Cut Distance.
|
ICLR | 2025 | 4 |
| Learning Efficient Positional Encodings with Graph Neural Networks.
|
ICLR | 2025 | 19 |
| What is Wrong with Perplexity for Long-context Language Modeling?
|
ICLR | 2025 | 0 |
| An Information Criterion for Controlled Disentanglement of Multimodal Data.
|
ICLR | 2025 | 0 |
| Beyond Interpretability: The Gains of Feature Monosemanticity on Model Robustness.
|
ICLR | 2025 | 0 |
| Computing Optimal Regularizers for Online Linear Optimization.
|
COLT | 2025 | 0 |
| Position: Future Directions in the Theory of Graph Machine Learning.
|
ICML | 2024 | 19 |
| The Empirical Impact of Neural Parameter Symmetries, or Lack Thereof.
|
NIPS/NeurIPS | 2024 | 19 |
| A Universal Class of Sharpness-Aware Minimization Algorithms.
|
ICML | 2024 | 12 |
| A Theoretical Understanding of Self-Correction through In-context Alignment.
|
NIPS/NeurIPS | 2024 | 57 |
| On the Role of Attention Masks and LayerNorm in Transformers.
|
NIPS/NeurIPS | 2024 | 35 |
| Simplicity Bias via Global Convergence of Sharpness Minimization.
|
ICML | 2024 | 3 |
| Can Looped Transformers Learn to Implement Multi-step Gradient Descent for In-context Learning?
|
ICML | 2024 | 39 |
| In-Context Symmetries: Self-Supervised Learning through Contextual World Models.
|
NIPS/NeurIPS | 2024 | 7 |
| On the hardness of learning under symmetries.
|
ICLR | 2024 | 14 |
| A Canonicalization Perspective on Invariant and Equivariant Learning.
|
NIPS/NeurIPS | 2024 | 21 |
| Understanding the Role of Equivariance in Self-supervised Learning.
|
NIPS/NeurIPS | 2024 | 7 |
| Sample Complexity Bounds for Estimating Probability Divergences under Invariances.
|
ICML | 2024 | 0 |
| Are Graph Neural Networks Optimal Approximation Algorithms?
|
NIPS/NeurIPS | 2024 | 0 |
| A Poincaré Inequality and Consistency Results for Signal Sampling on Large Graphs.
|
ICLR | 2024 | 0 |
| Structuring Representation Geometry with Rotationally Equivariant Contrastive Learning.
|
ICLR | 2024 | 0 |
| Context is Environment.
|
ICLR | 2024 | 0 |
| On the Stability of Expressive Positional Encodings for Graphs.
|
ICLR | 2024 | 0 |
| Efficiently predicting high resolution mass spectra with graph neural networks.
|
ICML | 2023 | 23 |
| The Power of Recursion in Graph Neural Networks for Counting Substructures.
|
AISTATS | 2023 | 11 |
| What is the Inductive Bias of Flatness Regularization? A Study of Deep Matrix Factorization Models.
|
NIPS/NeurIPS | 2023 | 9 |
| Limits, approximation and size transferability for GNNs on sparse graphs via graphops.
|
NIPS/NeurIPS | 2023 | 17 |
| Expressive Sign Equivariant Networks for Spectral Geometric Learning.
|
NIPS/NeurIPS | 2023 | 19 |
| InfoOT: Information Maximizing Optimal Transport.
|
ICML | 2023 | 0 |
| The Exact Sample Complexity Gain from Invariances for Kernel Regression.
|
NIPS/NeurIPS | 2023 | 0 |
| Sign and Basis Invariant Networks for Spectral Graph Representation Learning.
|
ICLR | 2023 | 0 |
| Tree Mover's Distance: Bridging Graph Metrics and Stability of Graph Neural Networks.
|
NIPS/NeurIPS | 2022 | 48 |
| Training invariances and the low-rank phenomenon: beyond linear networks.
|
ICLR | 2022 | 38 |
| Robust Contrastive Learning against Noisy Views.
|
CVPR | 2022 | 95 |
| On the generalization of learning algorithms that do not converge.
|
NIPS/NeurIPS | 2022 | 12 |
| Optimization and Adaptive Generalization of Three layer Neural Networks.
|
ICLR | 2022 | 1 |
| Neural Set Function Extensions: Learning with Discrete Functions in High Dimensions.
|
NIPS/NeurIPS | 2022 | 14 |
| Optimization of Graph Neural Networks: Implicit Acceleration by Skip Connections and More Depth.
|
ICML | 2021 | 86 |
| Information Obfuscation of Graph Neural Networks.
|
ICML | 2021 | 0 |
| Scaling up Continuous-Time Markov Chains Helps Resolve Underspecification.
|
NIPS/NeurIPS | 2021 | 10 |
| Measuring Generalization with Optimal Transport.
|
NIPS/NeurIPS | 2021 | 30 |
| What training reveals about neural network complexity.
|
NIPS/NeurIPS | 2021 | 12 |
| Can contrastive learning avoid shortcut solutions?
|
NIPS/NeurIPS | 2021 | 164 |
| Contrastive Learning with Hard Negative Samples.
|
ICLR | 2021 | 0 |
| How Neural Networks Extrapolate: From Feedforward to Graph Neural Networks.
|
ICLR | 2021 | 0 |
| Complexity of Finding Stationary Points of Nonconvex Nonsmooth Functions.
|
ICML | 2020 | 90 |
| IDEAL: Inexact DEcentralized Accelerated Augmented Lagrangian Method.
|
NIPS/NeurIPS | 2020 | 22 |
| Strength from Weakness: Fast Learning Using Weak Supervision.
|
ICML | 2020 | 35 |
| Estimating Generalization under Distribution Shifts via Domain-Invariant Representations.
|
ICML | 2020 | 71 |
| Generalization and Representational Limits of Graph Neural Networks.
|
ICML | 2020 | 357 |
| Distributionally Robust Bayesian Optimization.
|
AISTATS | 2020 | 91 |
| Debiased Contrastive Learning.
|
NIPS/NeurIPS | 2020 | 681 |
| Testing Determinantal Point Processes.
|
NIPS/NeurIPS | 2020 | 2 |
| Optimal approximation for unconstrained non-submodular minimization.
|
ICML | 2020 | 0 |
| Adaptive Sampling for Stochastic Risk-Averse Learning.
|
NIPS/NeurIPS | 2020 | 0 |
| What Can Neural Networks Reason About?
|
ICLR | 2020 | 0 |
| Distributionally Robust Optimization and Generalization in Kernel Methods.
|
NIPS/NeurIPS | 2019 | 148 |
| Are Girls Neko or Shōjo? Cross-Lingual Alignment of Non-Isomorphic Embeddings with Iterative Normalization.
|
ACL | 2019 | 63 |
| Flexible Modeling of Diversity with Strongly Log-Concave Distributions.
|
NIPS/NeurIPS | 2019 | 12 |
| Learning Generative Models across Incomparable Spaces.
|
ICML | 2019 | 118 |
| Towards Optimal Transport with Global Invariances.
|
AISTATS | 2019 | 0 |
| Distributionally Robust Submodular Maximization.
|
AISTATS | 2019 | 0 |
| How Powerful are Graph Neural Networks?
|
ICLR | 2019 | 0 |
| ResNet with one-neuron hidden layers is a Universal Approximator.
|
NIPS/NeurIPS | 2018 | 245 |
| Provable Variational Inference for Constrained Log-Submodular Models.
|
NIPS/NeurIPS | 2018 | 5 |
| Representation Learning on Graphs with Jumping Knowledge Networks.
|
ICML | 2018 | 2285 |
| Adversarially Robust Optimization with Gaussian Processes.
|
NIPS/NeurIPS | 2018 | 136 |
| Discrete Sampling using Semigradient-based Product Mixtures.
|
UAI | 2018 | 2 |
| Exponentiated Strongly Rayleigh Distributions.
|
NIPS/NeurIPS | 2018 | 14 |
| Streaming Non-Monotone Submodular Maximization: Personalized Video Summarization on the Fly.
|
AAAI | 2018 | 0 |
| Structured Optimal Transport.
|
AISTATS | 2018 | 0 |
| Batched Large-scale Bayesian Optimization in High-dimensional Spaces.
|
AISTATS | 2018 | 0 |
| Robust Budget Allocation via Continuous Submodular Functions.
|
ICML | 2017 | 58 |
| Max-value Entropy Search for Efficient Bayesian Optimization.
|
ICML | 2017 | 460 |
| Polynomial time algorithms for dual volume sampling.
|
NIPS/NeurIPS | 2017 | 31 |
| Parallel Streaming Wasserstein Barycenters.
|
NIPS/NeurIPS | 2017 | 92 |
| Batched High-dimensional Bayesian Optimization via Structural Kernel Learning.
|
ICML | 2017 | 132 |
| Focused model-learning and planning for non-Gaussian continuous state-action systems.
|
ICRA | 2017 | 0 |
| Deep Metric Learning via Facility Location.
|
CVPR | 2017 | 0 |
| Cooperative Graphical Models.
|
NIPS/NeurIPS | 2016 | 1 |
| Fast DPP Sampling for Nystrom with Application to Kernel Methods.
|
ICML | 2016 | 76 |
| Fast Mixing Markov Chains for Strongly Rayleigh Measures, DPPs, and Constrained Sampling.
|
NIPS/NeurIPS | 2016 | 39 |
| Gaussian quadrature for matrix inverse forms with applications.
|
ICML | 2016 | 0 |
| Efficient Sampling for k-Determinantal Point Processes.
|
AISTATS | 2016 | 0 |
| Optimization as Estimation with Gaussian Processes in Bandit Settings.
|
AISTATS | 2016 | 0 |
| Deep Metric Learning via Lifted Structured Feature Embedding.
|
CVPR | 2016 | 0 |
| On learning to localize objects with minimal supervision.
|
ICML | 2014 | 253 |
| Monotone Closure of Relaxed Constraints in Submodular Optimization: Connections Between Minimization and Maximization.
|
UAI | 2014 | 36 |
| On the Convergence Rate of Decomposable Submodular Function Minimization.
|
NIPS/NeurIPS | 2014 | 44 |
| Learning Scalable Discriminative Dictionary with Sample Relatedness.
|
CVPR | 2014 | 22 |
| Weakly-supervised Discovery of Visual Pattern Configurations.
|
NIPS/NeurIPS | 2014 | 166 |
| Parallel Double Greedy Submodular Maximization.
|
NIPS/NeurIPS | 2014 | 40 |
| Submodular meets Structured: Finding Diverse Subsets in Exponentially-Large Structured Item Sets.
|
NIPS/NeurIPS | 2014 | 70 |
| Optimistic Concurrency Control for Distributed Unsupervised Learning.
|
NIPS/NeurIPS | 2013 | 35 |
| Curvature and Optimal Algorithms for Learning and Minimizing Submodular Functions.
|
NIPS/NeurIPS | 2013 | 115 |
| A Principled Deep Random Field Model for Image Segmentation.
|
CVPR | 2013 | 75 |
| Fast Semidifferential-based Submodular Function Optimization.
|
ICML | 2013 | 111 |
| Reflection methods for user-friendly submodular optimization.
|
NIPS/NeurIPS | 2013 | 80 |
| Submodularity beyond submodular energies: Coupling edges in graph cuts.
|
CVPR | 2011 | 220 |
| On fast approximate submodular minimization.
|
NIPS/NeurIPS | 2011 | 63 |
| Approximation Bounds for Inference using Cooperative Cuts.
|
ICML | 2011 | 26 |
| Online Submodular Minimization for Combinatorial Structures.
|
ICML | 2011 | 38 |
| Solution stability in linear programming relaxations: graph partitioning and unsupervised learning.
|
ICML | 2009 | 44 |
| Consistent Minimization of Clustering Objective Functions.
|
NIPS/NeurIPS | 2007 | 15 |
| Fast Kernel ICA using an Approximate Newton Method.
|
AISTATS | 2007 | 18 |