A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
The paper addresses the gap between theoretical and practical confidence set widths in universal inference.
The estimation of probabilities of default (PDs) for low default portfolios by means of upper confidence bounds is a well established procedure in many financial institutions. However, there are often discussions within the institutions or between institutions and supervisors about which confidence level to use for the…
New method for accurate uncertainty estimation in deep learning predictions.
COME replaces entropy minimization to prevent model collapse.
Robust MDPs (RMDPs) can be used to compute policies with provable worst-case guarantees in reinforcement learning. The quality and robustness of an RMDP solution are determined by the ambiguity set---the set of plausible transition probabilities---which is usually constructed as a multi-dimensional confidence region. E…
The study examines methods to correct measurement error in nutritional epidemiology studies.
A new protocol evaluates small machine learning improvements conservatively.
HAMBO estimates policy performance by hallucinating worst-case trajectories, providing valid lower bounds.
Robustness is important for sequential decision making in a stochastic dynamic environment with uncertain probabilistic parameters. We address the problem of using robust MDPs (RMDPs) to compute policies with provable worst-case guarantees in reinforcement learning. The quality and robustness of an RMDP solution is det…
Develops methods for inference after detecting a change in sequential data.
New method improves level set estimation with theoretical guarantees.
New framework tightens certified robustness gaps in machine learning models.
New algorithm reduces pricing error by a factor of T^2/3.
Combines multiple OPE estimators into a more accurate and efficient estimate.
In recent years, there has been significant progress in applying deep reinforcement learning (RL) for solving challenging problems across a wide variety of domains. Nevertheless, convergence of various methods has been shown to suffer from inconsistencies, due to algorithmic instability and variance, as well as stochas…
We consider the problem of online planning in a Markov Decision Process when given only access to a generative model, restricted to open-loop policies - i.e. sequences of actions - and under budget constraint. In this setting, the Open-Loop Optimistic Planning (OLOP) algorithm enjoys good theoretical guarantees but is …
Companies try to maximize their profits by recovering returned products of highly uncertain quality and quantity. In this paper, a reverse logistics network for an Original Equipment Manufacturer (OEM) is presented. Returned products are selected for remanufacturing or scrapping, based on their quality and proportional…
Most bandit algorithm designs are purely theoretical. Therefore, they have strong regret guarantees, but also are often too conservative in practice. In this work, we pioneer the idea of algorithm design by minimizing the empirical Bayes regret, the average regret over problem instances sampled from a known distributio…
Paper proves impossible for large language models to control hallucinations without sacrificing other properties.
In this paper we consider the problem of inference on a class of sets describing a collection of admissible models as solutions to a single smooth inequality. Classical and recent examples include, among others, the Hansen-Jagannathan (HJ) sets of admissible stochastic discount factors, Markowitz-Fama (MF) sets of mean…
New offline RL algorithms tackle partial data coverage with optimal performance and practicality.
We consider the performance of the bootstrap in high-dimensions for the setting of linear regression, where but is not close to zero. We consider ordinary least-squares as well as robust regression methods and adopt a minimalist performance requirement: can the bootstrap give us good confidence intervals fo…
New sampling bounds improve uniform coverage verification in machine learning.
New approach improves adversarial robustness without sacrificing natural generalization.
CADRO optimizes DRO by reducing conservatism through cost-aware ambiguity sets.
Theoretical analysis confirms non-conservative algorithms can converge to optimal policies.
Study finds conserved quantities for two types of curves on conformal sphere.
Survey on conservation laws for geometric PDEs.
The article discusses conservation laws for polyharmonic maps and their applications.
PPI uses predictions to improve inference from incomplete data.
Paper presents a reduction-based framework for conservative bandits and RL with improved lower and upper bounds.
In batch reinforcement learning (RL), one often constrains a learned policy to be close to the behavior (data-generating) policy, e.g., by constraining the learned action distribution to differ from the behavior policy by some maximum degree that is the same at each state. This can cause batch RL to be overly conservat…
I consider the existence and structure of conservation laws for the general class of evolutionary scalar second-order differential equations with parabolic symbol. First I calculate the linearized characteristic cohomology for such equations. This provides an auxiliary differential equation satisfied by the conservatio…
New asymptotic e-values improve inference by eliminating data-dependent scaling inefficiency.
Non-trivial conservation law found for a specific system.
This work connects symmetries and conserved quantities in machine learning.
Proposes a conservative exploration method for RL agents.
Conservation law for weakly harmonic mappings in high dimensions.
The conservation laws of the third order quasilinear scalar evolution equations are considered via differential system and characteristic cohomology. We find a subspace of 2 forms in the infinite prolonged space in which every conservation law has a unique representative. The structure of this subspace naturally gives …
Given a vector field on a manifold M, we define a globally conserved quantity to be a differential form whose Lie derivative is exact. Integrals of conserved quantities over suitable submanifolds are constant under time evolution, the Kelvin circulation theorem being a well-known special case. More generally, conserved…
We study higher-order conservation laws of the non-linearizable elliptic Poisson equation as elements of the characteristic cohomology of the associated exterior differential system. The theory of characteristic cohomology determines a normal form for diffe…
New conservation laws found for polyharmonic maps in critical dimension.
A challenging problem in complex networks is the network reconstruction problem from data. This work deals with a class of networks denoted as conserved networks, in which a flow associated with every edge and the flows are conserved at all non-source and non-sink nodes. We propose a novel polynomial time algorithm to …
MC-LSTM extends LSTM to conserve mass in neural networks.
The paper studies symmetries and conservation laws of non-diagonalisable hydrodynamic systems.
We present a connection between the Killing fields that arise in the loop-group approach to integrable systems and conservation laws viewed as elements of the characteristic cohomology. We use the connection to generate the complete set of conservation laws (as elements of the characteristic cohomology) for the Tzitzei…
This paper introduces a novel framework to construct the region of attraction (ROA) of a power system centered around a stable equilibrium by using stable state trajectories of system dynamics. Most existing works on estimating ROA rely on analytical Lyapunov functions, which are subject to two limitations: the analyti…
A new algorithm balances exploration and exploitation in online decision-making.