Search Results for author:
Found 7 papers, 4 papers with code
Training Question Answering Models From Synthetic Data
On the SQuAD1. 1 question answering task, we achieve higher accuracy using solely synthetic questions and answers than when using the SQuAD1. 1 training set questions alone.
Compressing Gradient Optimizers via Count-Sketches
The problem is becoming more severe as deep learning models continue to grow larger in order to learn from complex, large-scale datasets.
Ultra Large-Scale Feature Selection using Count-Sketches
We demonstrate that MISSION accurately and efficiently performs feature selection on real-world, large-scale datasets with billions of dimensions.
MISSION: Ultra Large-Scale Feature Selection using Count-Sketches
We demonstrate that MISSION accurately and efficiently performs feature selection on real-world, large-scale datasets with billions of dimensions.
A New Unbiased and Efficient Class of LSH-Based Samplers and Estimators for Partition Function Computation in Log-Linear Models
We propose a new sampling scheme and an unbiased estimator that estimates the partition function accurately in sub-linear time.
Scalable and Sustainable Deep Learning via Randomized Hashing
A unique property of the proposed hashing based back-propagation is that the updates are always sparse.
