4 papers
From Trees to Continuous Embeddings and Back: Hyperbolic Hierarchical Clustering
Ines Chami, Albert Gu, Vaggos Chatziafratis +1
Similarity-based Hierarchical Clustering (HC) is a classical unsupervised machine learning algorithm that has traditionally been solved with heuristic algorithms like Average-Linka…
Model Patching: Closing the Subgroup Performance Gap with Data Augmentation
Karan Goel, Albert Gu, Yixuan Li +1
Classifiers in machine learning are often brittle when deployed. Particularly concerning are models with inconsistent performance on specific subgroups of a class, e.g., exhibiting…
Improving the Gating Mechanism of Recurrent Neural Networks
Albert Gu, Caglar Gulcehre, Tom Le Paine +2
Gating mechanisms are widely used in neural network models, where they allow gradients to backpropagate more easily through depth or time. However, their saturation property introd…
Sparse Recovery for Orthogonal Polynomial Transforms
Anna Gilbert, Albert Gu, Christopher Re +2
In this paper we consider the following sparse recovery problem. We have query access to a vector $\vx \in \R^N$ such that $\vhx = \vF \vx$ is -sparse (or nearly -sparse) for…