Stefanie Jegelka

Jon Schneider

CoRR, 2024

Learning Linear Attention in Polynomial Time.

[BibT_eX]

[DOI]

CoRR, 2024

Learning on LoRAs: GL-Equivariant Processing of Low-Rank Weight Spaces for Large Finetuned Models.

[BibT_eX]

[DOI]

CoRR, 2024

The Heterophilic Graph Learning Handbook: Benchmarks, Models, Theoretical Analysis, Applications and Challenges.

[BibT_eX]

[DOI]

CoRR, 2024

The Empirical Impact of Neural Parameter Symmetries, or Lack Thereof.

[BibT_eX]

[DOI]

CoRR, 2024

On the Role of Attention Masks and LayerNorm in Transformers.

[BibT_eX]

[DOI]

CoRR, 2024

A Theoretical Understanding of Self-Correction through In-context Alignment.

[BibT_eX]

[DOI]

CoRR, 2024

A Canonization Perspective on Invariant and Equivariant Learning.

[BibT_eX]

[DOI]

CoRR, 2024

In-Context Symmetries: Self-Supervised Learning through Contextual World Models.

[BibT_eX]

[DOI]

CoRR, 2024

How to Craft Backdoors with Unlabeled Data Alone?

[BibT_eX]

[DOI]

CoRR, 2024

Future Directions in Foundations of Graph Machine Learning.

[BibT_eX]

[DOI]

CoRR, 2024

A Universal Class of Sharpness-Aware Minimization Algorithms.

[BibT_eX]

[DOI]

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Sample Complexity Bounds for Estimating Probability Divergences under Invariances.

[BibT_eX]

[DOI]

Proceedings of the Forty-first International Conference on Machine Learning, 2024

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

[BibT_eX]

[DOI]

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Simplicity Bias via Global Convergence of Sharpness Minimization.

[BibT_eX]

[DOI]

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Position: Future Directions in the Theory of Graph Machine Learning.

[BibT_eX]

[DOI]

Proceedings of the Forty-first International Conference on Machine Learning, 2024

A Poincaré Inequality and Consistency Results for Signal Sampling on Large Graphs.

[BibT_eX]

[DOI]

Thien Le

Luana Ruiz

Proceedings of the Twelfth International Conference on Learning Representations, 2024

On the hardness of learning under symmetries.

[BibT_eX]

[DOI]

Proceedings of the Twelfth International Conference on Learning Representations, 2024

On the Stability of Expressive Positional Encodings for Graphs.

[BibT_eX]

[DOI]

Proceedings of the Twelfth International Conference on Learning Representations, 2024

Context is Environment.

[BibT_eX]

[DOI]

Proceedings of the Twelfth International Conference on Learning Representations, 2024

Structuring Representation Geometry with Rotationally Equivariant Contrastive Learning.

[BibT_eX]

[DOI]

Proceedings of the Twelfth International Conference on Learning Representations, 2024

2023

On the Stability of Expressive Positional Encodings for Graph Neural Networks.

[BibT_eX]

[DOI]

CoRR, 2023

Are Graph Neural Networks Optimal Approximation Algorithms?

[BibT_eX]

[DOI]

CoRR, 2023

The Inductive Bias of Flatness Regularization for Deep Matrix Factorization.

[BibT_eX]

[DOI]

CoRR, 2023

The Exact Sample Complexity Gain from Invariances for Kernel Regression on Manifolds.

[BibT_eX]

[DOI]

CoRR, 2023

Tetris-inspired detector with neural network for radiation mapping.

[BibT_eX]

[DOI]

CoRR, 2023

Debiasing Vision-Language Models via Biased Prompts.

[BibT_eX]

[DOI]

CoRR, 2023

The Exact Sample Complexity Gain from Invariances for Kernel Regression.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Expressive Sign Equivariant Networks for Spectral Geometric Learning.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

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

[BibT_eX]

[DOI]

Thien Le

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

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

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Efficiently predicting high resolution mass spectra with graph neural networks.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2023

InfoOT: Information Maximizing Optimal Transport.

[BibT_eX]

[DOI]

David Alvarez-Melis

Proceedings of the International Conference on Machine Learning, 2023

Sign and Basis Invariant Networks for Spectral Graph Representation Learning.

[BibT_eX]

[DOI]

Derek Lim

Joshua David Robinson

Proceedings of the Eleventh International Conference on Learning Representations, 2023

The Power of Recursion in Graph Neural Networks for Counting Substructures.

[BibT_eX]

[DOI]

Derek Lim

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2023

2022

Graph Embeddings: Theory meets Practice (Dagstuhl Seminar 22132).

[BibT_eX]

[DOI]

Dagstuhl Reports, 2022

Optimal algorithms for group distributionally robust optimization and beyond.

[BibT_eX]

[DOI]

Tasuku Soma

CoRR, 2022

Theory of Graph Neural Networks: Representation and Learning.

[BibT_eX]

[DOI]

CoRR, 2022

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

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

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

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

On the generalization of learning algorithms that do not converge.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Training invariances and the low-rank phenomenon: beyond linear networks.

[BibT_eX]

[DOI]

Thien Le

Proceedings of the Tenth International Conference on Learning Representations, 2022

Optimization and Adaptive Generalization of Three layer Neural Networks.

[BibT_eX]

[DOI]

Jonathan A. Kelner

Proceedings of the Tenth International Conference on Learning Representations, 2022

Robust Contrastive Learning against Noisy Views.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022

2021

Can contrastive learning avoid shortcut solutions?

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

What training reveals about neural network complexity.

[BibT_eX]

[DOI]

Andreas Loukas

Marinos Poiitis

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Scaling up Continuous-Time Markov Chains Helps Resolve Underspecification.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Measuring Generalization with Optimal Transport.

[BibT_eX]

[DOI]

Youssef Mroueh

Kristjan H. Greenewald

Antonio Torralba

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Optimization of Graph Neural Networks: Implicit Acceleration by Skip Connections and More Depth.

[BibT_eX]

[DOI]

Proceedings of the 38th International Conference on Machine Learning, 2021

Information Obfuscation of Graph Neural Networks.

[BibT_eX]

[DOI]

Proceedings of the 38th International Conference on Machine Learning, 2021

How Neural Networks Extrapolate: From Feedforward to Graph Neural Networks.

[BibT_eX]

[DOI]

Proceedings of the 9th International Conference on Learning Representations, 2021

Contrastive Learning with Hard Negative Samples.

[BibT_eX]

[DOI]

Joshua David Robinson

Proceedings of the 9th International Conference on Learning Representations, 2021

2020

Inorganic Materials Synthesis Planning with Literature-Trained Neural Networks.

[BibT_eX]

[DOI]

Edward Kim

Zach Jensen

Alexander van Grootel

J. Chem. Inf. Model., 2020

Counting Substructures with Higher-Order Graph Neural Networks: Possibility and Impossibility Results.

[BibT_eX]

[DOI]

CoRR, 2020

Graph Adversarial Networks: Protecting Information against Adversarial Attacks.

[BibT_eX]

[DOI]

CoRR, 2020

On the Complexity of Minimizing Convex Finite Sums Without Using the Indices of the Individual Functions.

[BibT_eX]

[DOI]

CoRR, 2020

Testing Determinantal Point Processes.

[BibT_eX]

[DOI]

Maryam Aliakbarpour

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Adaptive Sampling for Stochastic Risk-Averse Learning.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Debiased Contrastive Learning.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

IDEAL: Inexact DEcentralized Accelerated Augmented Lagrangian Method.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Complexity of Finding Stationary Points of Nonconvex Nonsmooth Functions.

[BibT_eX]

[DOI]

Proceedings of the 37th International Conference on Machine Learning, 2020

Strength from Weakness: Fast Learning Using Weak Supervision.

[BibT_eX]

[DOI]

Joshua Robinson

Proceedings of the 37th International Conference on Machine Learning, 2020

Optimal approximation for unconstrained non-submodular minimization.

[BibT_eX]

[DOI]

Marwa El Halabi

Proceedings of the 37th International Conference on Machine Learning, 2020

Generalization and Representational Limits of Graph Neural Networks.

[BibT_eX]

[DOI]

Vikas K. Garg

Tommi S. Jaakkola

Proceedings of the 37th International Conference on Machine Learning, 2020

Estimating Generalization under Distribution Shifts via Domain-Invariant Representations.

[BibT_eX]

[DOI]

Antonio Torralba

Proceedings of the 37th International Conference on Machine Learning, 2020

What Can Neural Networks Reason About?

[BibT_eX]

[DOI]

Proceedings of the 8th International Conference on Learning Representations, 2020

Distributionally Robust Bayesian Optimization.

[BibT_eX]

[DOI]

Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics, 2020

2019

Sensor Array Design Through Submodular Optimization.

[BibT_eX]

[DOI]

Gal Shulkind

Gregory W. Wornell

IEEE Trans. Inf. Theory, 2019

The Role of Embedding Complexity in Domain-invariant Representations.

[BibT_eX]

[DOI]

Antonio Torralba

CoRR, 2019

Minimizing approximately submodular functions.

[BibT_eX]

[DOI]

Marwa El Halabi

CoRR, 2019

Distributionally Robust Optimization and Generalization in Kernel Methods.

[BibT_eX]

[DOI]

Matthew Staib

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Flexible Modeling of Diversity with Strongly Log-Concave Distributions.

[BibT_eX]

[DOI]

Joshua Robinson

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Learning Generative Models across Incomparable Spaces.

[BibT_eX]

[DOI]

Proceedings of the 36th International Conference on Machine Learning, 2019

How Powerful are Graph Neural Networks?

[BibT_eX]

[DOI]

Proceedings of the 7th International Conference on Learning Representations, 2019

Distributionally Robust Submodular Maximization.

[BibT_eX]

[DOI]

Matthew Staib

Bryan Wilder

Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics, 2019

Towards Optimal Transport with Global Invariances.

[BibT_eX]

[DOI]

David Alvarez-Melis

Tommi S. Jaakkola

Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics, 2019

Are Girls Neko or Shōjo? Cross-Lingual Alignment of Non-Isomorphic Embeddings with Iterative Normalization.

[BibT_eX]

[DOI]

Mozhi Zhang

Keyulu Xu

Jordan L. Boyd-Graber

Proceedings of the 57th Conference of the Association for Computational Linguistics, 2019

2018

Robust GANs against Dishonest Adversaries.

[BibT_eX]

[DOI]

Zhi Xu

CoRR, 2018

Discrete Sampling using Semigradient-based Product Mixtures.

[BibT_eX]

[DOI]

Proceedings of the Thirty-Fourth Conference on Uncertainty in Artificial Intelligence, 2018

Exponentiated Strongly Rayleigh Distributions.

[BibT_eX]

[DOI]

Zelda E. Mariet

Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

ResNet with one-neuron hidden layers is a Universal Approximator.

[BibT_eX]

[DOI]

Hongzhou Lin

Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

Provable Variational Inference for Constrained Log-Submodular Models.

[BibT_eX]

[DOI]

Josip Djolonga

Andreas Krause

Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

Adversarially Robust Optimization with Gaussian Processes.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

Representation Learning on Graphs with Jumping Knowledge Networks.

[BibT_eX]

[DOI]

Proceedings of the 35th International Conference on Machine Learning, 2018

Distributional Adversarial Networks.

[BibT_eX]

[DOI]

Proceedings of the 6th International Conference on Learning Representations, 2018

Batched Large-scale Bayesian Optimization in High-dimensional Spaces.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2018

Structured Optimal Transport.

[BibT_eX]

[DOI]

David Alvarez-Melis

Tommi S. Jaakkola

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2018

Streaming Non-Monotone Submodular Maximization: Personalized Video Summarization on the Fly.

[BibT_eX]

[DOI]

Baharan Mirzasoleiman

Andreas Krause

Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, 2018

2017

Graph cuts with interacting edge weights: examples, approximations, and algorithms.

[BibT_eX]

[DOI]

Math. Program., 2017

Graph-Sparse Logistic Regression.

[BibT_eX]

[DOI]

CoRR, 2017

Parallel Streaming Wasserstein Barycenters.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 2017

Polynomial time algorithms for dual volume sampling.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 2017

Focused model-learning and planning for non-Gaussian continuous state-action systems.

[BibT_eX]

[DOI]

Zi Wang

Leslie Pack Kaelbling

Tomás Lozano-Pérez

Proceedings of the 2017 IEEE International Conference on Robotics and Automation, 2017

Batched High-dimensional Bayesian Optimization via Structural Kernel Learning.

[BibT_eX]

[DOI]

Proceedings of the 34th International Conference on Machine Learning, 2017

Max-value Entropy Search for Efficient Bayesian Optimization.

[BibT_eX]

[DOI]

Zi Wang

Proceedings of the 34th International Conference on Machine Learning, 2017

Robust Budget Allocation via Continuous Submodular Functions.

[BibT_eX]

[DOI]

Matthew Staib

Proceedings of the 34th International Conference on Machine Learning, 2017

Multiple wavelength sensing array design.

[BibT_eX]

[DOI]

Gal Shulkind

Gregory W. Wornell

Proceedings of the 2017 IEEE International Conference on Acoustics, 2017

Deep Metric Learning via Facility Location.

[BibT_eX]

[DOI]

Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, 2017

2016

Learnable Structured Clustering Framework for Deep Metric Learning.

[BibT_eX]

[DOI]

CoRR, 2016

Fast Sampling for Strongly Rayleigh Measures with Application to Determinantal Point Processes.

[BibT_eX]

[DOI]

CoRR, 2016

Auxiliary Image Regularization for Deep CNNs with Noisy Labels.

[BibT_eX]

[DOI]

Proceedings of the 4th International Conference on Learning Representations, 2016

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

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, 2016

Cooperative Graphical Models.

[BibT_eX]

[DOI]

Josip Djolonga

Sebastian Tschiatschek

Andreas Krause

Proceedings of the Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, 2016

Gaussian quadrature for matrix inverse forms with applications.

[BibT_eX]

[DOI]

Proceedings of the 33nd International Conference on Machine Learning, 2016

Fast DPP Sampling for Nystrom with Application to Kernel Methods.

[BibT_eX]

[DOI]

Proceedings of the 33nd International Conference on Machine Learning, 2016

Deep Metric Learning via Lifted Structured Feature Embedding.

[BibT_eX]

[DOI]

Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition, 2016

Optimization as Estimation with Gaussian Processes in Bandit Settings.

[BibT_eX]

[DOI]

Zi Wang

Bolei Zhou

Proceedings of the 19th International Conference on Artificial Intelligence and Statistics, 2016

Efficient Sampling for k-Determinantal Point Processes.

[BibT_eX]

[DOI]

Proceedings of the 19th International Conference on Artificial Intelligence and Statistics, 2016

2015

Bounds on bilinear inverse forms via Gaussian quadrature with applications.

[BibT_eX]

[DOI]

CoRR, 2015

Convex Optimization for Parallel Energy Minimization.

[BibT_eX]

[DOI]

K. S. Sesh Kumar

Álvaro Barbero Jiménez

Francis R. Bach

CoRR, 2015

Inferring and Learning from Neuronal Correspondences.

[BibT_eX]

[DOI]

Ashish Kapoor

Edward Paxon Frady

William B. Kristan Jr.

Eric Horvitz

CoRR, 2015

2014

An Interactive Approach to Solving Correspondence Problems.

[BibT_eX]

[DOI]

Ashish Kapoor

Eric Horvitz

Int. J. Comput. Vis., 2014

One-Bit Object Detection: On learning to localize objects with minimal supervision.

[BibT_eX]

[DOI]

CoRR, 2014

Graph Cuts with Interacting Edge Costs - Examples, Approximations, and Algorithms.

[BibT_eX]

[DOI]

CoRR, 2014

Monotone Closure of Relaxed Constraints in Submodular Optimization: Connections Between Minimization and Maximization.

[BibT_eX]

[DOI]

Rishabh K. Iyer

Proceedings of the Thirtieth Conference on Uncertainty in Artificial Intelligence, 2014

Weakly-supervised Discovery of Visual Pattern Configurations.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems 2014, 2014

Submodular meets Structured: Finding Diverse Subsets in Exponentially-Large Structured Item Sets.

[BibT_eX]

[DOI]

Adarsh Prasad

Dhruv Batra

Proceedings of the Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems 2014, 2014

Parallel Double Greedy Submodular Maximization.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems 2014, 2014

On the Convergence Rate of Decomposable Submodular Function Minimization.

[BibT_eX]

[DOI]

Robert Nishihara

Michael I. Jordan

Proceedings of the Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems 2014, 2014

On learning to localize objects with minimal supervision.

[BibT_eX]

[DOI]

Proceedings of the 31th International Conference on Machine Learning, 2014

Learning Scalable Discriminative Dictionary with Sample Relatedness.

[BibT_eX]

[DOI]

Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition, 2014

Efficient and accurate clustering for large-scale genetic mapping.

[BibT_eX]

[DOI]

Proceedings of the 2014 IEEE International Conference on Bioinformatics and Biomedicine, 2014

2013

Optimistic Concurrency Control for Distributed Unsupervised Learning.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 26: 27th Annual Conference on Neural Information Processing Systems 2013. Proceedings of a meeting held December 5-8, 2013

Reflection methods for user-friendly submodular optimization.

[BibT_eX]

[DOI]

Francis R. Bach

Proceedings of the Advances in Neural Information Processing Systems 26: 27th Annual Conference on Neural Information Processing Systems 2013. Proceedings of a meeting held December 5-8, 2013

Curvature and Optimal Algorithms for Learning and Minimizing Submodular Functions.

[BibT_eX]

[DOI]

Rishabh K. Iyer

Proceedings of the Advances in Neural Information Processing Systems 26: 27th Annual Conference on Neural Information Processing Systems 2013. Proceedings of a meeting held December 5-8, 2013

Fast Semidifferential-based Submodular Function Optimization.

[BibT_eX]

[DOI]

Rishabh K. Iyer

Proceedings of the 30th International Conference on Machine Learning, 2013

A Principled Deep Random Field Model for Image Segmentation.

[BibT_eX]

[DOI]

Pushmeet Kohli

Anton Osokin

Proceedings of the 2013 IEEE Conference on Computer Vision and Pattern Recognition, 2013

2012

Combinatorial problems with submodular coupling in machine learning and computer vision.

[BibT_eX]

[DOI]

Stefanie Sabrina Jegelka

PhD thesis, 2012

2011

On fast approximate submodular minimization.

[BibT_eX]

[DOI]

Hui Lin

Proceedings of the Advances in Neural Information Processing Systems 24: 25th Annual Conference on Neural Information Processing Systems 2011. Proceedings of a meeting held 12-14 December 2011, 2011

Approximation Bounds for Inference using Cooperative Cuts.

[BibT_eX]

[DOI]

Proceedings of the 28th International Conference on Machine Learning, 2011

Online Submodular Minimization for Combinatorial Structures.

[BibT_eX]

[DOI]