This paper proposes a comprehensive benchmarking framework for evaluating mutual information estimation methods on complex, realistic data using copula theory.

This paper analyzes Best-of-$N$ preference data, deriving explicit reward targets for independent-reference variants and establishing design principles for choosing $N$ and the base distribution to op…

The paper introduces Score Broadcast and Decorrelation (SBD), a general theoretical framework that unifies broadcast-based credit assignment across various differentiable loss functions by leveraging…

This paper introduces the Value Causal Markov Condition (v-CMC) for linking causality and utility, and develops its foundations.

The paper introduces PRAXIS, a novel algorithm that efficiently approximates the computation of 'Rashomon sets' for decision trees, significantly reducing memory and runtime complexity.

This paper characterizes how estimation error in covariance matrices affects the global minimum-variance portfolio and derives a decision geometry for regret.

This paper provides a theoretical analysis of Cumulative Prospect Theory (CPT) for multi-objective and multi-criteria decision-making under risk, focusing on Neilson's definitions of aversion and prop…

This paper studies the existence of polynomial measures of dependence between two random variables that satisfy the data processing inequality and vanish on independence. It proves that no such polyno…

The paper introduces novel compatibility and incompatibility scores to evaluate collections of bivariate causal statements, providing a way to assess causal claims when ground truth is unavailable.

The paper establishes that for quantifier-free dependence logic formulas, the property of k-coherence is equivalent to first-order rewritability, and analyzes the computational complexity of checking…

This paper characterizes proper binary classification from positive-only samples, revealing a rich landscape that differs from standard PAC learning.

This paper introduces Distributional Random Forests, which replace mean-based CART splitting with criteria that compare full conditional response distributions in candidate children. The authors syste…

The paper formalizes the concept of a causal pathway for rare events, showing that testable implications can be derived solely from this pathway abstraction, simplifying complex causal modeling.