Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
Performance Gaps Between Open-Loop, Certainty-Equivalent, and Optimal Control Under Action-Dependent Observations
Leo Maynard-Zhang, Sunmook Choi, Yahya Sattar +3
In dynamical systems, feedback can improve performance by allowing decisions to depend on past observations, rather than being designed a priori. Under full observation, the curren…
cs.LG2026
Two-Layer Linear Auto-Regressive Models Estimate Latent States
Yahya Sattar, Sunmook Choi, Leo Maynard-Zhang +3
Auto-regressive models have emerged as powerful tools for sequential data, from language to video. Understanding how and why these models learn latent representations remains an op…
cs.LG2025
Explore-then-Commit for Nonstationary Linear Bandits with Latent Dynamics
Sunmook Choi, Yahya Sattar, Yassir Jedra +2
We study a nonstationary bandit problem where rewards depend on both actions and latent states, the latter governed by unknown linear dynamics. Crucially, the state dynamics also d…