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 David Alvarez-Melis

Optimizing Functionals on the Space of Probabilities with Input Convex Neural Networks


Jun 14, 2021
David Alvarez-Melis, Yair Schiff, Youssef Mroueh


  Access Paper or Ask Questions

A Human-Centered Interpretability Framework Based on Weight of Evidence


Apr 27, 2021
David Alvarez-Melis, Harmanpreet Kaur, Hal Daumé III, Hanna Wallach, Jennifer Wortman Vaughan


  Access Paper or Ask Questions

Gradient Flows in Dataset Space


Oct 24, 2020
David Alvarez-Melis, Nicolò Fusi


  Access Paper or Ask Questions

Geometric Dataset Distances via Optimal Transport


Feb 07, 2020
David Alvarez-Melis, Nicolò Fusi


  Access Paper or Ask Questions

Unsupervised Hierarchy Matching with Optimal Transport over Hyperbolic Spaces


Nov 06, 2019
David Alvarez-Melis, Youssef Mroueh, Tommi S. Jaakkola


  Access Paper or Ask Questions

Probabilistic Bias Mitigation in Word Embeddings


Oct 31, 2019
Hailey James-Sorenson, David Alvarez-Melis

* 4 pages, 4 figures, Workshop on Human-Centric Machine Learning at NeurIPS 2019 

  Access Paper or Ask Questions

Weight of Evidence as a Basis for Human-Oriented Explanations


Oct 29, 2019
David Alvarez-Melis, Hal Daumé III, Jennifer Wortman Vaughan, Hanna Wallach

* Human-Centric Machine Learning (HCML) Workshop @ NeurIPS 2019 

  Access Paper or Ask Questions

Towards Robust, Locally Linear Deep Networks


Jul 07, 2019
Guang-He Lee, David Alvarez-Melis, Tommi S. Jaakkola

* Published in International Conference on Learning Representations (ICLR), 2019 

  Access Paper or Ask Questions

Learning Generative Models across Incomparable Spaces


May 15, 2019
Charlotte Bunne, David Alvarez-Melis, Andreas Krause, Stefanie Jegelka

* Proceedings of Machine Learning Research (PMLR), 97 (2019) 
* International Conference on Machine Learning (ICML) 

  Access Paper or Ask Questions

Functional Transparency for Structured Data: a Game-Theoretic Approach


Feb 26, 2019
Guang-He Lee, Wengong Jin, David Alvarez-Melis, Tommi S. Jaakkola


  Access Paper or Ask Questions

Gromov-Wasserstein Alignment of Word Embedding Spaces


Aug 31, 2018
David Alvarez-Melis, Tommi S. Jaakkola

* EMNLP 2018 

  Access Paper or Ask Questions

Game-Theoretic Interpretability for Temporal Modeling


Jun 30, 2018
Guang-He Lee, David Alvarez-Melis, Tommi S. Jaakkola


  Access Paper or Ask Questions

Towards Optimal Transport with Global Invariances


Jun 25, 2018
David Alvarez-Melis, Stefanie Jegelka, Tommi S. Jaakkola


  Access Paper or Ask Questions

On the Robustness of Interpretability Methods


Jun 21, 2018
David Alvarez-Melis, Tommi S. Jaakkola

* presented at 2018 ICML Workshop on Human Interpretability in Machine Learning (WHI 2018), Stockholm, Sweden 

  Access Paper or Ask Questions

Towards Robust Interpretability with Self-Explaining Neural Networks


Jun 20, 2018
David Alvarez-Melis, Tommi S. Jaakkola


  Access Paper or Ask Questions

Structured Optimal Transport


Dec 17, 2017
David Alvarez-Melis, Tommi S. Jaakkola, Stefanie Jegelka


  Access Paper or Ask Questions

A causal framework for explaining the predictions of black-box sequence-to-sequence models


Nov 14, 2017
David Alvarez-Melis, Tommi S. Jaakkola

* 12 Pages, EMNLP 2017 

  Access Paper or Ask Questions

Distributional Adversarial Networks


Jul 09, 2017
Chengtao Li, David Alvarez-Melis, Keyulu Xu, Stefanie Jegelka, Suvrit Sra


  Access Paper or Ask Questions

Word, graph and manifold embedding from Markov processes


Sep 18, 2015
Tatsunori B. Hashimoto, David Alvarez-Melis, Tommi S. Jaakkola


  Access Paper or Ask Questions