Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Stefanie Jegelka

Stefanie Jegelka

Massachusetts Institute of Technology

Scaling up Continuous-Time Markov Chains Helps Resolve Underspecification


Jul 06, 2021
Alkis Gotovos, Rebekka Burkholz, John Quackenbush, Stefanie Jegelka


  Access Paper or Ask Questions

Can contrastive learning avoid shortcut solutions?


Jun 21, 2021
Joshua Robinson, Li Sun, Ke Yu, Kayhan Batmanghelich, Stefanie Jegelka, Suvrit Sra

* Preprint 

  Access Paper or Ask Questions

What training reveals about neural network complexity


Jun 08, 2021
Andreas Loukas, Marinos Poiitis, Stefanie Jegelka

* 31 pages, 8 figures 

  Access Paper or Ask Questions

Measuring Generalization with Optimal Transport


Jun 07, 2021
Ching-Yao Chuang, Youssef Mroueh, Kristjan Greenewald, Antonio Torralba, Stefanie Jegelka


  Access Paper or Ask Questions

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


May 26, 2021
Keyulu Xu, Mozhi Zhang, Stefanie Jegelka, Kenji Kawaguchi


  Access Paper or Ask Questions

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


Dec 06, 2020
Behrooz Tahmasebi, Stefanie Jegelka


  Access Paper or Ask Questions

Contrastive Learning with Hard Negative Samples


Oct 09, 2020
Joshua Robinson, Ching-Yao Chuang, Suvrit Sra, Stefanie Jegelka


  Access Paper or Ask Questions

Graph Adversarial Networks: Protecting Information against Adversarial Attacks


Oct 07, 2020
Peiyuan Liao, Han Zhao, Keyulu Xu, Tommi Jaakkola, Geoffrey Gordon, Stefanie Jegelka, Ruslan Salakhutdinov

* Our code is available at https://github.com/liaopeiyuan/GAL 

  Access Paper or Ask Questions

How Neural Networks Extrapolate: From Feedforward to Graph Neural Networks


Oct 01, 2020
Keyulu Xu, Jingling Li, Mozhi Zhang, Simon S. Du, Ken-ichi Kawarabayashi, Stefanie Jegelka


  Access Paper or Ask Questions

Testing Determinantal Point Processes


Aug 09, 2020
Khashayar Gatmiry, Maryam Aliakbarpour, Stefanie Jegelka


  Access Paper or Ask Questions

Estimating Generalization under Distribution Shifts via Domain-Invariant Representations


Jul 06, 2020
Ching-Yao Chuang, Antonio Torralba, Stefanie Jegelka

* International Conference on Machine Learning, 2020 
* arXiv admin note: text overlap with arXiv:1910.05804 

  Access Paper or Ask Questions

Debiased Contrastive Learning


Jul 05, 2020
Ching-Yao Chuang, Joshua Robinson, Lin Yen-Chen, Antonio Torralba, Stefanie Jegelka


  Access Paper or Ask Questions

IDEAL: Inexact DEcentralized Accelerated Augmented Lagrangian Method


Jun 11, 2020
Yossi Arjevani, Joan Bruna, Bugra Can, Mert Gürbüzbalaban, Stefanie Jegelka, Hongzhou Lin


  Access Paper or Ask Questions

Distributionally Robust Bayesian Optimization


Mar 22, 2020
Johannes Kirschner, Ilija Bogunovic, Stefanie Jegelka, Andreas Krause

* Accepted at AISTATS 2020 

  Access Paper or Ask Questions

Strength from Weakness: Fast Learning Using Weak Supervision


Feb 19, 2020
Joshua Robinson, Stefanie Jegelka, Suvrit Sra

* 21 pages, 8 figures 

  Access Paper or Ask Questions

On Complexity of Finding Stationary Points of Nonsmooth Nonconvex Functions


Feb 16, 2020
Jingzhao Zhang, Hongzhou Lin, Stefanie Jegelka, Ali Jadbabaie, Suvrit Sra


  Access Paper or Ask Questions

Generalization and Representational Limits of Graph Neural Networks


Feb 14, 2020
Vikas K. Garg, Stefanie Jegelka, Tommi Jaakkola


  Access Paper or Ask Questions

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


Feb 09, 2020
Yossi Arjevani, Amit Daniely, Stefanie Jegelka, Hongzhou Lin


  Access Paper or Ask Questions

Adaptive Sampling for Stochastic Risk-Averse Learning


Oct 28, 2019
Sebastian Curi, Kfir. Y. Levy, Stefanie Jegelka, Andreas Krause


  Access Paper or Ask Questions

The Role of Embedding Complexity in Domain-invariant Representations


Oct 13, 2019
Ching-Yao Chuang, Antonio Torralba, Stefanie Jegelka


  Access Paper or Ask Questions

Flexible Modeling of Diversity with Strongly Log-Concave Distributions


Jun 12, 2019
Joshua Robinson, Suvrit Sra, Stefanie Jegelka


  Access Paper or Ask Questions

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


Jun 05, 2019
Mozhi Zhang, Keyulu Xu, Ken-ichi Kawarabayashi, Stefanie Jegelka, Jordan Boyd-Graber

* ACL 2019 

  Access Paper or Ask Questions

What Can Neural Networks Reason About?


May 31, 2019
Keyulu Xu, Jingling Li, Mozhi Zhang, Simon S. Du, Ken-ichi Kawarabayashi, Stefanie Jegelka


  Access Paper or Ask Questions

Minimizing approximately submodular functions


May 29, 2019
Marwa El Halabi, Stefanie Jegelka


  Access Paper or Ask Questions