Research Archive

In this work, we introduce a localized, MDL-based divergence measure that quantifies the structural complexity of induced subgraphs relative to a global reference model. The measure compares the compressibility of local neighborhoods under globally fitted and locally optimized comparator models while penalizing model flexibility, yielding a statistically grounded notion of local structural surprise. The results show that the measure converges under controlled ablations, is robust to sampling choices, and detects meaningful structural irregularities that are invariant to geometric embedding. This framework generalizes MDL-based network analysis to arbitrary information graphs and provides a principled bridge between global structure and agent-level experience.

The Lab investigates the math behind a machine's right to forget, and the human's right to be forgotten as presented by the seminal Sekhari paper.

We propose an MDL-based measure of network structural complexity. The method utilizes the two-phase MDL approach for describing random and nonrandom variation.

We review Sinha and Mahajan's take on the sufficiency of an information state. We're such fans, we decide to take it even further.

A primer on entropy, mutual information, and variational inference.

Continuing our Foundations series, we explore sigma-algebras—the mathematical scaffolding that makes probability rigorous and connects abstract theory to real-world randomness in our models.