The Shaped Transformer: Attention Models in the Infinite Depth-and-Width Limit

Item #:

075280-2363

Details

DOI: https://doi.org/10.52202/075280-2363
Author(s): Bobby He, Thomas Hofmann, Chuning Li, Mufan Li, Chris Maddison, Lorenzo Noci, Dan Roy
Pages: 54250-54281 (32 pages)
Format: PDF Paper Download
Conference: Advances in Neural Information Processing Systems 36
Date/Location: Held 10-16 December 2023, New Orleans, Louisiana, USA.
Series: Advances in Neural Information Processing Systems 36
Publisher: Neural Information Processing Systems Foundation, Inc. (NeurIPS)

DOI: https://doi.org/10.52202/075280-2363
Author(s): Bobby He, Thomas Hofmann, Chuning Li, Mufan Li, Chris Maddison, Lorenzo Noci, Dan Roy
Pages: 54250-54281 (32 pages)
Format: PDF Paper Download
Conference: Advances in Neural Information Processing Systems 36
Date/Location: Held 10-16 December 2023, New Orleans, Louisiana, USA.
Series: Advances in Neural Information Processing Systems 36
Publisher: Neural Information Processing Systems Foundation, Inc. (NeurIPS)