low-dimensional-subspace

Tag

Cards List
#low-dimensional-subspace

@Tiberiu_Musat_: What really happens during LLM training? Can we ever disentangle those billions of interacting parameters? In our lates…

X AI KOLs Timeline · 3d ago Cached

This preprint reveals that under certain data symmetries, LLM training dynamics can be reduced to a low-dimensional subspace, making analysis more tractable and interpretable, with each coordinate corresponding to a clear mechanism.

0 favorites 0 likes
#low-dimensional-subspace

Stochastic Linear Bandits with Partially Observed Actions

arXiv cs.LG · 2026-07-13 Cached

This paper studies stochastic linear bandits where the agent only observes a random subset of action coordinates, proving that sublinear regret is possible when actions have low intrinsic dimension, and proposes the TOFU-POV algorithm with theoretical guarantees.

0 favorites 0 likes
← Back to home

Submit Feedback