PolySketchFormer: Fast Transformers via Sketching Polynomial Kernels

The quadratic time and memory complexity inherent to self-attention mechanisms, with respect to sequence length, presents a critical computational bottleneck in the training and deployment of large-scale Transformer-based language models. Recent theoretical results indicate the intractability of sub-quadratic softmax attention approximation under reasonable complexity assumptions. This paper addresses this challenge by first demonstrating that polynomial attention with high degree can effectively replace softmax without sacrificing model quality. Next, we develop polynomial sketching techniques from numerical linear algebra to achieve linear-time …

approximation assumptions attention attention mechanisms challenge complexity computational cs.lg deployment language language models memory paper polynomial scale self-attention softmax training transformer transformers via