Search Results for author:
Found 4 papers, 3 papers with code
Cyclic Data Parallelism for Efficient Parallelism of Deep Neural Networks
Training large deep learning models requires parallelization techniques to scale.
Can Forward Gradient Match Backpropagation?
Forward Gradients - the idea of using directional derivatives in forward differentiation mode - have recently been shown to be utilizable for neural network training while avoiding problems generally associated with backpropagation gradient computation, such as locking and memorization requirements.
Paraphrases do not explain word analogies
Many types of distributional word embeddings (weakly) encode linguistic regularities as directions (the difference between "jump" and "jumped" will be in a similar direction to that of "walk" and "walked," and so on).
Analogies minus analogy test: measuring regularities in word embeddings
Vector space models of words have long been claimed to capture linguistic regularities as simple vector translations, but problems have been raised with this claim.
