3 papers
cs.LG2025
Trellis: Learning to Compress Key-Value Memory in Attention Models
Mahdi Karami, Ali Behrouz, Praneeth Kacham +1
Transformers, while powerful, suffer from quadratic computational complexity and the ever-growing Key-Value (KV) cache of the attention mechanism. This paper introduces Trellis, a…
cs.DS2024
Approximating the Top Eigenvector in Random Order Streams
Praneeth Kacham, David P. Woodruff
When rows of an matrix are given in a stream, we study algorithms for approximating the top eigenvector of the matrix (equivalently, the top right singula…
cs.LG2024
LevAttention: Time, Space, and Streaming Efficient Algorithm for Heavy Attentions
Ravindran Kannan, Chiranjib Bhattacharyya, Praneeth Kacham +1
A central problem related to transformers can be stated as follows: given two matrices and , and a non-negative function , define the matrix as follows:…