This paper addresses the problem of inferring a directed network from nodal measurements using graph convolutional filters and identifies the diffusion filter and network topology.

This paper introduces an entropy-based method to generate multiple plausible causal maps (atlases) that accurately reflect the inherent structural ambiguity in complex systems, moving beyond single, o…

This paper introduces gradient inference, a new approach to developing sound and efficient gradient estimators for probabilistic programs by reducing gradient estimation to a related probabilistic inf…

The paper introduces ProbMoE, a probabilistic routing framework that tackles the non-differentiability of top-$k$ routing in Mixture-of-Experts (MoE) models, achieving strong performance with improved…

The paper proposes a semi-relaxed Gromov-Wasserstein objective to estimate the latent connectivity structure of large-scale networks, achieving statistically consistent and efficient recovery of the u…

Taurus is a single-machine system for efficient Graph Neural Network (GNN) inference on large-scale graphs that do not fit in RAM, using source-centric broadcasts and a pipelined GPU-CPU-SSD hierarchy…

This paper introduces a new approach for scalable causal discovery in directed acyclic graphs (DAGs) with clustered data and local cluster-level effects.

This paper investigates the tradeoff between parameter estimation and predictive accuracy in probabilistic temporal graphs, proposing a causal framework for evaluation.

The paper proposes $D^3$, a dynamic graph-constrained scheduling framework that optimizes LLM training order by modeling sample interactions as a dynamic influence graph.

The paper presents a framework for model selection and parameter estimation using large language models and neural simulation-based inference.

The paper extends modular dynamic Bayesian networks (MDBNs) to model non-Markovian queues, providing the first causal metamodeling technique for such systems with significant speedup.

The paper introduces a framework for composing deep probabilistic models using five specific factor-graph primitives that guarantee closed-form variational inference, thereby preserving tractability i…

CausalForge is a framework for automated theoretical research in causal inference using Lean proof assistant, including a foundational library and a self-improving agent.

This paper proposes a scalable topological learning framework for higher-order graph representation by introducing simplified and factored cellular Weisfeiler Leman tests and a novel random walk metho…

This paper introduces a correction-aware network model to study the spread of erroneous claims in communication networks and characterizes the intersection of reliability and error control constraints…

The paper introduces Bayesian Membership Privacy (BMP), a sampling-aware framework that accurately quantifies node-level membership privacy in Graph Neural Networks by treating graph sampling probabil…

The paper theoretically explains that optimizing LLMs solely on outcomes leads to brittle reasoning (Reward-Induced Manifold Collapse) by favoring low-complexity shortcuts, and proposes process-based…

This paper introduces DiPhon, a diffusion framework for size-scalable graph generation, using a continuous diffusion process on the graphon space and a discretized graph-level process.