Stefanie Jegelka

Data Augmentation: A Fourier Analysis Perspective COLT 2026 Efficient Learning and Symmetry Discovery under Exact Invariances COLT 2026 An Information Criterion for Controlled Disentanglement of Multimodal Data ICLR 2025 A Robust Kernel Statistical Test of Invariance: Detecting Subtle Asymmetries AISTATS 2025 Beyond Interpretability: The Gains of Feature Monosemanticity on Model Robustness ICLR 2025 Beyond Matryoshka: Revisiting Sparse Coding for Adaptive Representation ICML 2025 Computing Optimal Regularizers for Online Linear Optimization COLT 2025 Generalization Bounds for Canonicalization: A Comparative Study with Group Averaging ICLR 2025 Generalization, Expressivity, and Universality of Graph Neural Networks on Attributed Graphs ICLR 2025 Higher-Order Graphon Neural Networks: Approximation and Cut Distance ICLR 2025 Learning Efficient Positional Encodings with Graph Neural Networks ICLR 2025 Learning with Exact Invariances in Polynomial Time ICML 2025 On the Emergence of Position Bias in Transformers ICML 2025 Regularity in Canonicalized Models: A Theoretical Perspective AISTATS 2025 What is Wrong with Perplexity for Long-context Language Modeling? ICLR 2025 A Canonicalization Perspective on Invariant and Equivariant Learning NeurIPS 2024 A Poincaré Inequality and Consistency Results for Signal Sampling on Large Graphs ICLR 2024 Are Graph Neural Networks Optimal Approximation Algorithms? NeurIPS 2024 A Theoretical Understanding of Self-Correction through In-context Alignment NeurIPS 2024 A Universal Class of Sharpness-Aware Minimization Algorithms ICML 2024 Can Looped Transformers Learn to Implement Multi-step Gradient Descent for In-context Learning? ICML 2024 Context is Environment ICLR 2024 In-Context Symmetries: Self-Supervised Learning through Contextual World Models NeurIPS 2024 On the hardness of learning under symmetries ICLR 2024 On the Role of Attention Masks and LayerNorm in Transformers NeurIPS 2024 On the Stability of Expressive Positional Encodings for Graphs ICLR 2024 Position: Future Directions in the Theory of Graph Machine Learning ICML 2024 Sample Complexity Bounds for Estimating Probability Divergences under Invariances ICML 2024 Simplicity Bias via Global Convergence of Sharpness Minimization ICML 2024 Structuring Representation Geometry with Rotationally Equivariant Contrastive Learning ICLR 2024 The Empirical Impact of Neural Parameter Symmetries, or Lack Thereof NeurIPS 2024 Understanding the Role of Equivariance in Self-supervised Learning NeurIPS 2024 Efficiently predicting high resolution mass spectra with graph neural networks ICML 2023 Expressive Sign Equivariant Networks for Spectral Geometric Learning NeurIPS 2023 InfoOT: Information Maximizing Optimal Transport ICML 2023 Limits, approximation and size transferability for GNNs on sparse graphs via graphops NeurIPS 2023 Sign and Basis Invariant Networks for Spectral Graph Representation Learning ICLR 2023 The Exact Sample Complexity Gain from Invariances for Kernel Regression NeurIPS 2023 The Power of Recursion in Graph Neural Networks for Counting Substructures AISTATS 2023 What is the Inductive Bias of Flatness Regularization? A Study of Deep Matrix Factorization Models NeurIPS 2023 Neural Set Function Extensions: Learning with Discrete Functions in High Dimensions NeurIPS 2022 On the generalization of learning algorithms that do not converge NeurIPS 2022 Optimization and Adaptive Generalization of Three layer Neural Networks ICLR 2022 Robust Contrastive Learning Against Noisy Views CVPR 2022 Training invariances and the low-rank phenomenon: beyond linear networks ICLR 2022 Tree Mover's Distance: Bridging Graph Metrics and Stability of Graph Neural Networks NeurIPS 2022 Can contrastive learning avoid shortcut solutions? NeurIPS 2021 Contrastive Learning with Hard Negative Samples ICLR 2021 How Neural Networks Extrapolate: From Feedforward to Graph Neural Networks ICLR 2021 Information Obfuscation of Graph Neural Networks ICML 2021 Measuring Generalization with Optimal Transport NeurIPS 2021 Optimization of Graph Neural Networks: Implicit Acceleration by Skip Connections and More Depth ICML 2021 Scaling up Continuous-Time Markov Chains Helps Resolve Underspecification NeurIPS 2021 What training reveals about neural network complexity NeurIPS 2021 Adaptive Sampling for Stochastic Risk-Averse Learning NeurIPS 2020 Complexity of Finding Stationary Points of Nonconvex Nonsmooth Functions ICML 2020 Debiased Contrastive Learning NeurIPS 2020 Distributionally Robust Bayesian Optimization AISTATS 2020 Estimating Generalization under Distribution Shifts via Domain-Invariant Representations ICML 2020 Generalization and Representational Limits of Graph Neural Networks ICML 2020 IDEAL: Inexact DEcentralized Accelerated Augmented Lagrangian Method NeurIPS 2020 Optimal approximation for unconstrained non-submodular minimization ICML 2020 Strength from Weakness: Fast Learning Using Weak Supervision ICML 2020 Testing Determinantal Point Processes NeurIPS 2020 What Can Neural Networks Reason About? ICLR 2020 Are Girls Neko or Shōjo? Cross-Lingual Alignment of Non-Isomorphic Embeddings with Iterative Normalization ACL 2019 Distributionally Robust Optimization and Generalization in Kernel Methods NeurIPS 2019 Distributionally Robust Submodular Maximization AISTATS 2019 Flexible Modeling of Diversity with Strongly Log-Concave Distributions NeurIPS 2019 How Powerful are Graph Neural Networks? ICLR 2019 Learning Generative Models across Incomparable Spaces ICML 2019 Towards Optimal Transport with Global Invariances AISTATS 2019 Adversarially Robust Optimization with Gaussian Processes NeurIPS 2018 Batched Large-scale Bayesian Optimization in High-dimensional Spaces AISTATS 2018 Exponentiated Strongly Rayleigh Distributions NeurIPS 2018 Provable Variational Inference for Constrained Log-Submodular Models NeurIPS 2018 Representation Learning on Graphs with Jumping Knowledge Networks ICML 2018 ResNet with one-neuron hidden layers is a Universal Approximator NeurIPS 2018 Structured Optimal Transport AISTATS 2018 Batched High-dimensional Bayesian Optimization via Structural Kernel Learning ICML 2017 Deep Metric Learning via Facility Location CVPR 2017 Max-value Entropy Search for Efficient Bayesian Optimization ICML 2017 Parallel Streaming Wasserstein Barycenters NeurIPS 2017 Polynomial time algorithms for dual volume sampling NeurIPS 2017 Robust Budget Allocation via Continuous Submodular Functions ICML 2017 Cooperative Graphical Models NeurIPS 2016 Deep Metric Learning via Lifted Structured Feature Embedding CVPR 2016 Efficient Sampling for k-Determinantal Point Processes AISTATS 2016 Fast DPP Sampling for Nystrom with Application to Kernel Methods ICML 2016 Fast Mixing Markov Chains for Strongly Rayleigh Measures, DPPs, and Constrained Sampling NeurIPS 2016 Gaussian quadrature for matrix inverse forms with applications ICML 2016 Optimization as Estimation with Gaussian Processes in Bandit Settings AISTATS 2016 Learning Scalable Discriminative Dictionary with Sample Relatedness CVPR 2014 On learning to localize objects with minimal supervision ICML 2014 On the Convergence Rate of Decomposable Submodular Function Minimization NeurIPS 2014 Parallel Double Greedy Submodular Maximization NeurIPS 2014 Submodular meets Structured: Finding Diverse Subsets in Exponentially-Large Structured Item Sets NeurIPS 2014 Weakly-supervised Discovery of Visual Pattern Configurations NeurIPS 2014 A Principled Deep Random Field Model for Image Segmentation CVPR 2013 Curvature and Optimal Algorithms for Learning and Minimizing Submodular Functions NeurIPS 2013 Fast Semidifferential-based Submodular Function Optimization ICML 2013 Optimistic Concurrency Control for Distributed Unsupervised Learning NeurIPS 2013 Reflection methods for user-friendly submodular optimization NeurIPS 2013 On fast approximate submodular minimization NeurIPS 2011 Consistent Minimization of Clustering Objective Functions NeurIPS 2007 Fast Kernel ICA using an Approximate Newton Method AISTATS 1999