AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Differentiable Range-Partition Entropy for Entropy-Sensitive Geometric Algorithms

Ibne Farabi Shihab, Sanjeda Akter, Anuj Sharma

NeurIPS 2026 · Architectures and efficiency › RNNs and normalization · approach: Differentiable optimization layers

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Introduces Differentiable Entropy Regularization (DER), a gradient-optimizable surrogate for range-partition entropy of learned geometric partitions, separating normalized and runtime-scaled entropy measures.

Problem

Range-partition entropy is a structural complexity measure in entropy-sensitive computational geometry, but it is not differentiable, so learned geometric partitions cannot be directly optimized for it.

Approach

A gradient-optimizable surrogate (DER) for the entropy of learned geometric partitions, with explicit separation between the normalized entropy H_norm(S) that DER optimizes and the runtime-scaled entropy H_work(S) = n · H(...).

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy