828 citations · 5.6k across the 171 of their papers we have counts for
7 papers · 1 filter
Gromov-Wasserstein Alignment of Word Embedding Spaces
David Alvarez-Melis, Tommi S. Jaakkola
Cross-lingual or cross-domain correspondences play key roles in tasks ranging from machine translation to transfer learning. Recently, purely unsupervised methods operating on mono…
The Variational Homoencoder: Learning to learn high capacity generative models from few examples
Luke B. Hewitt, Maxwell I. Nye, Andreea Gane +2
Hierarchical Bayesian methods can unify many related tasks (e.g. k-shot classification, conditional and unconditional generation) as inference within a single generative model. How…
Game-Theoretic Interpretability for Temporal Modeling
Guang-He Lee, David Alvarez-Melis, Tommi S. Jaakkola
Interpretability has arisen as a key desideratum of machine learning models alongside performance. Approaches so far have been primarily concerned with fixed dimensional inputs emp…
On the Robustness of Interpretability Methods
David Alvarez-Melis, Tommi S. Jaakkola
We argue that robustness of explanations---i.e., that similar inputs should give rise to similar explanations---is a key desideratum for interpretability. We introduce metrics to q…
Towards Optimal Transport with Global Invariances
David Alvarez-Melis, Stefanie Jegelka, Tommi S. Jaakkola
Many problems in machine learning involve calculating correspondences between sets of objects, such as point clouds or images. Discrete optimal transport provides a natural and suc…
Towards Robust Interpretability with Self-Explaining Neural Networks
David Alvarez-Melis, Tommi S. Jaakkola
Most recent work on interpretability of complex machine learning models has focused on estimating explanations for previously trained models around specific…