4 papers
Compute-Optimal Is Not Cluster-Optimal: Systems-Aware Scaling for Sparse Mixture-of-Experts
Soumajyoti Sarkar, Yuxin Tang, Sheng Zha
In large-scale pretraining, the algorithm, architecture, and systems decisions are conventionally made in disconnected stages. A scaling law stage selects an architecture and train…
DEM: Distribution Edited Model for Training with Mixed Data Distributions
Dhananjay Ram, Aditya Rawal, Momchil Hardalov +2
Training with mixed data distributions is a common and important part of creating multi-task and instruction-following models. The diversity of the data distributions and cost of j…
Pre-training Differentially Private Models with Limited Public Data
Zhiqi Bu, Xinwei Zhang, Mingyi Hong +2
The superior performance of large foundation models relies on the use of massive amounts of high-quality data, which often contain sensitive, private and copyrighted material that…
Extreme Miscalibration and the Illusion of Adversarial Robustness
Vyas Raina, Samson Tan, Volkan Cevher +3
Deep learning-based Natural Language Processing (NLP) models are vulnerable to adversarial attacks, where small perturbations can cause a model to misclassify. Adversarial Training…