No article text was recorded for this version.
computational hardness of attention
Version 1 of 113 papers36 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Fast Attention Requires Bounded Entries
- Blog: How to Capture Higher-order Correlations? Generalizing Matrix Softmax Attention to Kronecker Computation
- Blog: Subquadratic Algorithms and Hardness for Attention with Any Temperature
- Blog: Fast RoPE Attention: Combining the Polynomial Method and Fast Fourier Transform
- Blog: Tensor Attention Training: Provably Efficient Learning of Higher-order Transformers
- Blog: Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency
- Blog: Fast Gradient Computation for RoPE Attention in Almost Linear Time
- Blog: On Statistical Rates and Provably Efficient Criteria of Latent Diffusion Transformers (DiTs)
- Blog: On Computational Limits of Modern Hopfield Models: A Fine-Grained Complexity Analysis
- Blog: On The Computational Complexity of Self-Attention
- Blog: On the Expressive Flexibility of Self-Attention Matrices
- Blog: Two (narrow) heads are better than (an arbitrarily wide) one
- Blog: Provably learning a multi-head attention layer
History & citation
Current · Permanent link
- This direction split from The Bounded Entry Limit for Subquadratic Attention (77% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_computational_hardness_of_attention_f79c2fff,
title = {computational hardness of attention},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/computational-hardness-of-attention/rdr_f79c2fff3f6d49609aee53560ed49c5f},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_computational_hardness_of_attention_f79c2fff_v1,
title = {computational hardness of attention},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/computational-hardness-of-attention/rdr_f79c2fff3f6d49609aee53560ed49c5f/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}