
HoroPCA: Hyperbolic Dimensionality Reduction via Horospherical Projections
This paper studies Principal Component Analysis (PCA) for data lying in ...
read it

Kaleidoscope: An Efficient, Learnable Representation For All Structured Linear Maps
Modern neural network architectures use structured linear transformation...
read it

No Subclass Left Behind: FineGrained Robustness in CoarseGrained Classification Problems
In realworld classification tasks, each class often comprises multiple ...
read it

From Trees to Continuous Embeddings and Back: Hyperbolic Hierarchical Clustering
Similaritybased Hierarchical Clustering (HC) is a classical unsupervise...
read it

HiPPO: Recurrent Memory with Optimal Polynomial Projections
A central problem in learning from sequential data is representing cumul...
read it

Model Patching: Closing the Subgroup Performance Gap with Data Augmentation
Classifiers in machine learning are often brittle when deployed. Particu...
read it

Improving the Gating Mechanism of Recurrent Neural Networks
Gating mechanisms are widely used in neural network models, where they a...
read it

Sparse Recovery for Orthogonal Polynomial Transforms
In this paper we consider the following sparse recovery problem. We have...
read it

Learning Fast Algorithms for Linear Transforms Using Butterfly Factorizations
Fast linear transforms are ubiquitous in machine learning, including the...
read it

Learning Compressed Transforms with Low Displacement Rank
The low displacement rank (LDR) framework for structured matrices repres...
read it

Representation Tradeoffs for Hyperbolic Embeddings
Hyperbolic embeddings offer excellent quality with few dimensions when e...
read it

A Kernel Theory of Modern Data Augmentation
Data augmentation, a technique in which a training set is expanded with ...
read it
Albert Gu
is this you? claim profile