Search Results for author:
Found 2 papers, 0 papers with code
Channel-wise Hessian Aware trace-Weighted Quantization of Neural Networks
Recent paper proposes to use Hessian traces of weights and activations for mixed-precision quantization and achieves state-of-the-art results.
SAGA with Arbitrary Sampling
We study the problem of minimizing the average of a very large number of smooth functions, which is of key importance in training supervised learning models.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
