conftrace_

gradient concentration

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

data allocation (1) agent alignment (1) log-concave distribution (1) supervised fine-tuning (1) mixing time (1) hamiltonian monte carlo (1) markov chain monte carlo (1) reinforcement learning (1)

Papers

Consolidation or Adaptation? PRISM: Disentangling SFT and RL Data via Gradient Concentration ACL 2026 Logsmooth Gradient Concentration and Tighter Runtimes for Metropolized Hamiltonian Monte Carlo COLT 2020