22 citations · 84 across the 24 of their papers we have counts for
Showing 2022 · cs.LGShow all
2 papers · 2 filters
cs.LG2022★ 2 cited
A Theoretical View on Sparsely Activated Networks
Cenk Baykal, Nishanth Dikkala, Rina Panigrahy +2
Deep and wide neural networks successfully fit very complex functions today, but dense models are starting to be prohibitively expensive for inference. To mitigate this, one promis…
cs.LG2022★ 10 cited
Do More Negative Samples Necessarily Hurt in Contrastive Learning?
Pranjal Awasthi, Nishanth Dikkala, Pritish Kamath
Recent investigations in noise contrastive estimation suggest, both empirically as well as theoretically, that while having more "negative samples" in the contrastive loss improves…