786 citations · 3k across the 61 of their papers we have counts for
67 papers
Stochastic Optimization Under Power-Law Spectra: Tight Bounds and Shuffling Analysis
Thomas Dybdahl Ahle, Yaroslav Bulatov, Christopher De Sa +1
Recent work has established that power-law spectral conditions on data enable tight convergence bounds for deterministic gradient descent, resolving the conflict between classical…
Pixelated Butterfly: Simple and Efficient Sparse training for Neural Network Models
Tri Dao, Beidi Chen, Kaizhao Liang +4
Overparameterized neural networks generalize well but are expensive to train. Ideally, one would like to reduce their computational cost while retaining their generalization benefi…
Personalized Benchmarking with the Ludwig Benchmarking Toolkit
Avanika Narayan, Piero Molino, Karan Goel +2
The rapid proliferation of machine learning models across domains and deployment settings has given rise to various communities (e.g. industry practitioners) which seek to benchmar…
Metadata Shaping: Natural Language Annotations for the Tail
Simran Arora, Sen Wu, Enci Liu +1
Language models (LMs) have made remarkable progress, but still struggle to generalize beyond the training data to rare linguistic patterns. Since rare entities and facts are preval…
No Subclass Left Behind: Fine-Grained Robustness in Coarse-Grained Classification Problems
Nimit S. Sohoni, Jared A. Dunnmon, Geoffrey Angus +2
In real-world classification tasks, each class often comprises multiple finer-grained "subclasses." As the subclass labels are frequently unavailable, models trained using only the…
Bootleg: Chasing the Tail with Self-Supervised Named Entity Disambiguation
Laurel Orr, Megan Leszczynski, Simran Arora +4
A challenge for named entity disambiguation (NED), the task of mapping textual mentions to entities in a knowledge base, is how to disambiguate entities that appear rarely in the t…