Search papers, labs, and topics across Lattice.
Affiliation:
5
0
6
Agentic loops can now reliably stop with provable guarantees on proposal quality, even with imperfect verifiers.
LLM inference auctions unlock economic efficiency and user utility by enabling dynamic bidding for compute priority, outperforming static pricing tiers.
Trajectory-adaptive stopping rules can cut SGD iterations by several orders of magnitude while maintaining statistical validity and optimal decay rates.
Solving Blackwell approachability problems via Gradient Equilibrium oracles reveals a deep connection between these two seemingly distinct optimization frameworks.
Excluding features based on manipulability can lead to suboptimal predictions, revealing a critical flaw in standard feature selection practices.
