2 papers
cs.DS2026
Towards Tight Bounds for Streaming Attention
Justin Y. Chen, Ying Feng, Piotr Indyk +3
The attention mechanism is a cornerstone of modern transformer architectures. However, its expressive power comes at the cost of quadratic runtime and linear space usage. In partic…
cs.LG2026
Provable Quantization with Randomized Hadamard Transform
Ying Feng, Piotr Indyk, Michael Kapralov +2
Vector quantization via random projection followed by scalar quantization is a fundamental primitive in machine learning, with applications ranging from similarity search to federa…