Get Started
Research questionHow can batched Lipschitz narrowing achieve low regret when the zooming dimension is unknown?Batched Lipschitz narrowing typically uses the zooming dimension and constant to set its refinement schedule. Without them, the procedure must adapt its search scale while preserving effective regret and limited opportunities to update decisions.
Machine Learning
Research Paper
Statistical Machine Learning
Latest papersRecent research connected to this question, newest first.Dimension-Adaptive Batched Lipschitz Narrowing Without Knowing the Zooming DimensionThe source studies a Count-Adaptive BLiN algorithm that selects edge lengths from the number of cubes surviving elimination, without using the zooming dimension or zooming constant. It reports a regret rate of \(\widetilde{\mathcal O}_d(T^{(d_z+1)/(d_z+2)})\) with \(\mathcal O_d(\log\log T)\) batches, and cites an adaptive-grid lower bound establishing optimal \(\Theta_d(\log\log T)\) batch complexity when the zooming dimension is unknown.research paper · Sep 4, 2026
Related questions
How can batched entropic optimal transport stop updating converged instances without changing its stopping rule?When can reasoning LLMs reliably optimize numerical and semantically rich discrete search spaces in batches?How can teams estimate whether multiclass accuracy gains reduce optimization regret before building a model?How can noisy Lipschitz regression recover an unknown function uniformly on a general metric space?
Home
Topics
Search
Library