all AI news
Unraveling Attention via Convex Duality: Analysis and Interpretations of Vision Transformers. (arXiv:2205.08078v2 [cs.LG] UPDATED)
May 23, 2022, 1:12 a.m. | Arda Sahiner, Tolga Ergen, Batu Ozturkler, John Pauly, Morteza Mardani, Mert Pilanci
cs.CV updates on arXiv.org arxiv.org
Vision transformers using self-attention or its proposed alternatives have
demonstrated promising results in many image related tasks. However, the
underpinning inductive bias of attention is not well understood. To address
this issue, this paper analyzes attention through the lens of convex duality.
For the non-linear dot-product self-attention, and alternative mechanisms such
as MLP-mixer and Fourier Neural Operator (FNO), we derive equivalent
finite-dimensional convex problems that are interpretable and solvable to
global optimality. The convex programs lead to {\it block nuclear-norm …
More from arxiv.org / cs.CV updates on arXiv.org
Jobs in AI, ML, Big Data
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
Alternant Data Engineering
@ Aspire Software | Angers, FR
Senior Software Engineer, Generative AI
@ Google | Dublin, Ireland