Zobrazeno 1 - 10
of 24
pro vyhledávání: '"Devvrit"'
Autor:
Devvrit, Fnu, Duvvuri, Sai Surya, Anil, Rohan, Gupta, Vineet, Hsieh, Cho-Jui, Dhillon, Inderjit
Second-order methods hold significant promise for enhancing the convergence of deep neural network training; however, their large memory and computational demands have limited their practicality. Thus there is a need for scalable second-order methods
Externí odkaz:
http://arxiv.org/abs/2311.10085
Autor:
Gupta, Nilesh, Khatri, Devvrit, Rawat, Ankit S, Bhojanapalli, Srinadh, Jain, Prateek, Dhillon, Inderjit
Publikováno v:
ICLR 2024 camera-ready publication
Dual-encoder (DE) models are widely used in retrieval tasks, most commonly studied on open QA benchmarks that are often characterized by multi-class and limited training data. In contrast, their performance in multi-label and data-rich retrieval sett
Externí odkaz:
http://arxiv.org/abs/2310.10636
Autor:
Devvrit, Kudugunta, Sneha, Kusupati, Aditya, Dettmers, Tim, Chen, Kaifeng, Dhillon, Inderjit, Tsvetkov, Yulia, Hajishirzi, Hannaneh, Kakade, Sham, Farhadi, Ali, Jain, Prateek
Transformer models are deployed in a wide range of settings, from multi-accelerator clusters to standalone mobile phones. The diverse inference constraints in these scenarios necessitate practitioners to train foundation models such as PaLM 2, Llama,
Externí odkaz:
http://arxiv.org/abs/2310.07707
Autor:
Devvrit, Fnu, Krim-Yee, Aaron, Kumar, Nithish, MacGillivray, Gary, Seamone, Ben, Virgile, Virgélot, Xu, AnQi
This paper initiates the study of fractional eternal domination in graphs, a natural relaxation of the well-studied eternal domination problem. We study the connections to flows and linear programming in order to obtain results on the complexity of d
Externí odkaz:
http://arxiv.org/abs/2304.11795
Pruning schemes have been widely used in practice to reduce the complexity of trained models with a massive number of parameters. In fact, several practical studies have shown that if a pruned model is fine-tuned with some gradient-based updates it g
Externí odkaz:
http://arxiv.org/abs/2303.11453
Labelled data often comes at a high cost as it may require recruiting human labelers or running costly experiments. At the same time, in many practical scenarios, one already has access to a partially labelled, potentially biased dataset that can hel
Externí odkaz:
http://arxiv.org/abs/2106.06676
Developing robust models against adversarial perturbations has been an active area of research and many algorithms have been proposed to train individual robust models. Taking these pretrained robust models, we aim to study whether it is possible to
Externí odkaz:
http://arxiv.org/abs/2011.14031
Autor:
Fnu Devvrit, Aaron Krim-Yee, Nithish Kumar, Gary MacGillivray, Ben Seamone, Virgélot Virgile, AnQi Xu
Publikováno v:
Discussiones Mathematicae Graph Theory, Vol 44, Iss 4, p 1395 (2024)
Externí odkaz:
https://doaj.org/article/20f8a983054848289145fcd42a74b2b3
Autor:
Khatri, Devvrit, Komarov, Natasha, Krim-Yee, Aaron, Kumar, Nithish, Seamone, Ben, Virgile, Virgélot, Xu, AnQi
We consider the well-studied cops and robbers game in the context of oriented graphs, which has received surprisingly little attention to date. We examine the relationship between the cop numbers of an oriented graph and its underlying undirected gra
Externí odkaz:
http://arxiv.org/abs/1811.06155
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.