2 papers
stat.ML2026
On The Complexity of Best-Arm Identification in Non-Stationary Linear Bandits
Leo Maynard-Zhang, Zhihan Xiong, Kevin Jamieson +1
We study the fixed-budget best-arm identification (BAI) problem in non-stationary linear bandits. Concretely, given a fixed time budget , finite arm set $\mathcal{…
cs.LG2025
Gating is Weighting: Understanding Gated Linear Attention through In-context Learning
Yingcong Li, Davoud Ataee Tarzanagh, Ankit Singh Rawat +2
Linear attention methods offer a compelling alternative to softmax attention due to their efficiency in recurrent decoding. Recent research has focused on enhancing standard linear…