The paper derives a characterization of minimax risk for KV cache compression and maps it to practical design principles and an algorithm tested on LongBench.
Fast attention requires bounded entries.Advances in Neural Information Processing Systems, 36:63117–63135, 2023
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
The risk of KV cache compression
The paper derives a characterization of minimax risk for KV cache compression and maps it to practical design principles and an algorithm tested on LongBench.