Sotabase

Career

· Assistant Professor, Harvard University2023–
· Senior Researcher, Microsoft Research2021–
· Postdoctoral Researcher, Microsoft Research2019–2021
· Research Intern, Microsoft Research2018–2018
· PhD in Computer Science, Massachusetts Institute of Technology2014–2019
· Research Assistant, MIT CSAIL2014–2019
· Supplemental Researcher, IBM Research2013–2014
· M.S. in Mathematics, Courant Institute, New York University2011–2013
· Statistical Analyst, LasQuinceLetras Solutions2009–2010
· B.S. in Applied Mathematics, Instituto Tecnologico Autonomo de Mexico2006–2011

Publications (77)

Towards Robust Interpretability with Self-Explaining Neural Networks
Neural Information Processing Systems · 2018
1,072
cited
On the Robustness of Interpretability Methods
arXiv.org · 2018
597
cited
Gromov-Wasserstein Alignment of Word Embedding Spaces
Conference on Empirical Methods in Natural Language Processing · 2018
350
cited
Geometric Dataset Distances via Optimal Transport
Neural Information Processing Systems · 2020
239
cited
A causal framework for explaining the predictions of black-box sequence-to-sequence models
Conference on Empirical Methods in Natural Language Processing · 2017
211
cited
Topic Modeling in Twitter: Aggregating Tweets by Conversations
International Conference on Web and Social Media · 2016
120
cited
Learning Generative Models across Incomparable Spaces
International Conference on Machine Learning · 2019
118
cited
Tree-structured decoding with doubly-recurrent neural networks
International Conference on Learning Representations · 2016
105
cited
Word Embeddings as Metric Recovery in Semantic Spaces
Transactions of the Association for Computational Linguistics · 2016
91
cited
Towards Optimal Transport with Global Invariances
International Conference on Artificial Intelligence and Statistics · 2018
78
cited
Structured Optimal Transport
International Conference on Artificial Intelligence and Statistics · 2017
75
cited
Optimizing Functionals on the Space of Probabilities with Input Convex Neural Networks
Trans. Mach. Learn. Res. · 2021
64
cited
Tag-LLM: Repurposing General-Purpose LLMs for Specialized Domains
International Conference on Machine Learning · 2024
54
cited
Towards Robust, Locally Linear Deep Networks
International Conference on Learning Representations · 2019
48
cited
A Label is Worth a Thousand Images in Dataset Distillation
Neural Information Processing Systems · 2024
26
cited
Unsupervised Hierarchy Matching with Optimal Transport over Hyperbolic Spaces
International Conference on Artificial Intelligence and Statistics · 2019
26
cited
Distributional Adversarial Networks
International Conference on Learning Representations · 2017
24
cited
Dataset Dynamics via Gradient Flows in Probability Space
International Conference on Machine Learning · 2020
23
cited
Neural Unbalanced Optimal Transport via Cycle-Consistent Semi-Couplings
arXiv.org · 2022
23
cited
Weight of Evidence as a Basis for Human-Oriented Explanations
arXiv.org · 2019
22
cited
Sotabase
David Alvarez-Melis | Researcher Profile | Sotabase | Sotabase