From the 1 of 28 linked papers with an AI index.
Showing stat.MLShow all
2 papers · 1 filter
stat.ML2026
Thompson Sampling Is 2-Competitive for Mistakes
Mark Sellke, Gregory Valiant
The paper proves that Thompson sampling incurs at most twice the expected number of suboptimal arm selections as any other policy in Bayesian bandit settings, under independent arm…
stat.ML2024
No Free Prune: Information-Theoretic Barriers to Pruning at Initialization
Tanishq Kumar, Kevin Luo, Mark Sellke
The existence of "lottery tickets" arXiv:1803.03635 at or near initialization raises the tantalizing question of whether large models are necessary in deep learning, or whether spa…