arXiv research

Proposes new rule for ranking investment prospects over long horizons.

Introduces relative information gain for improving Gaussian process regression rates.

The study optimizes distribution estimation from samples with relative entropy error, adapting to sparse distributions.

The risk premium is one of main concepts in mathematical finance. It is a measure of the trade-offs investors make between return and risk and is defined by the excess return relative to the risk-free interest rate that is earned from an asset per one unit of risk. The purpose of this article is to determine upper and …

New bounds show polyhedral surrogates are optimal for generalization.

This research improves PAC-Bayesian bounds for classification tasks using convexified loss.

The paper examines utility maximization in markets with hidden Gaussian drift, finding restrictions on model parameters.

Estimating and assessing the risk of a large portfolio is an important topic in financial econometrics and risk management. The risk is often estimated by a substitution of a good estimator of the volatility matrix. However, the accuracy of such a risk estimator for large portfolios is largely unknown, and a simple ine…

Noise-ignorant empirical risk minimization achieves state-of-the-art performance on noisy data.

Improved PAC-Bayesian bounds by considering example difficulty.

New method targets relative risk heterogeneity in clinical trials.

AGCA approximates angular variation on the unit sphere, reducing extremal dependence problems to eigenanalysis.

Earlier studies have shown that stock market distributions can be well described by distributions derived from Tsallis entropy, which is a generalization of Shannon entropy to non-extensive systems. In this paper, Tsallis relative entropy (TRE), which is the generalization of Kullback-Leibler relative entropy (KLRE) to…

The paper optimizes portfolios using relative tail risk measures.

Unified framework for risk-aware policy learning in contextual bandits.

New regularization method reduces support of empirical risk minimization solutions.

Meta-learning bounds derived using PAC-Bayes theory for improved generalization.

We derive generalization and excess risk bounds for neural nets using a family of complexity measures based on a multilevel relative entropy. The bounds are obtained by introducing the notion of generated hierarchical coverings of neural nets and by using the technique of chaining mutual information introduced in Asadi…

Introduces factor risk measures to assess risk relative to multiple factors.

Study optimal investment decisions for diverse risk-tolerant agents.

The paper introduces a measure to assess the relative value of a delta-Symmetric Strangle under the Black-Scholes model.

Study causal inference under specific sampling methods with monotonicity assumptions.

Paper proposes a new framework to improve stability-based bounds in deep learning.

Develops asymptotic theory for deep Cox models to enable valid inference.

New method uses asymmetric Tsallis relative entropy for better risk assessment in financial portfolios.

New stability bounds for GD in overparameterised shallow nets without NTK assumptions.

Study optimizes portfolio to minimize relative drawdown duration, penalizing unfavorable performance states.

This paper improves risk bounds and calibration for smart predict-then-optimize method.

New model solves equity premium puzzle.

We show that Entropy-SGD (Chaudhari et al., 2017), when viewed as a learning algorithm, optimizes a PAC-Bayes bound on the risk of a Gibbs (posterior) classifier, i.e., a randomized classifier obtained by a risk-sensitive perturbation of the weights of a learned classifier. Entropy-SGD works by optimizing the bound's p…

Study dynamic risk measures with distributional uncertainty using optimal transport.

This paper compares two different frameworks recently introduced in the literature for measuring risk in a multi-period setting. The first corresponds to applying a single coherent risk measure to the cumulative future costs, while the second involves applying a composition of one-step coherent risk mappings. We summar…

Entropy asymmetry affects regularization in ERM, leading to biased solutions.

The paper analyzes the generalization performance of spectral clustering algorithms and proposes new methods to improve their effectiveness.

In the paper, we introduce the notion of a local regular supermartingale relative to a convex set of equivalent measures and prove for it the necessary and sufficient conditions of optional Doob decomposition in the discrete case. This Theorem is a generalization of the famous Doob decomposition onto the case of superm…

Study optimal portfolios for many players in a market model with random coefficients.

The study examines Nash equilibria in utility maximization games with multiplicative performance criteria.

We tackle imbalanced classification by weighting losses and derive robust risks.

The paper analyzes portfolio credit risk using Archimedean copulas and introduces efficient simulation methods.

The writers propose a mathematical Method for deriving risk weights which describe how a borrower's income, relative to their debt service obligations (serviceability) affects the probability of default of the loan. The Method considers the borrower's income not simply as a known quantity at the time the loan is made, …

We investigate the ergodic problem of growth-rate maximization under a class of risk constraints in the context of incomplete, Itô-process models of financial markets with random ergodic coefficients. Including {\em value-at-risk} (VaR), {\em tail-value-at-risk} (TVaR), and {\em limited expected loss} (LEL), these cons…

EP-learning framework improves causal contrast estimation efficiency.

Study uses CSIE to estimate portfolio volatility relative to market.

A machine learning model improves relative valuation of municipal bonds.

By analysing the restrictions that ensure the existence of capital market equilibrium, we show that the coefficient of relative risk aversion and the subjective discount factor cannot be high simultaneously as they are supposed to be to make the standard asset pricing consistent with financial stylised facts.

This paper introduces a relative model risk measure of a product priced with a given model, with respect to another reference model for which the market is assumed to be driven. This measure allows comparing products valued with different models (pricing hypothesis) under a homogeneous framework which allows concluding…

Paper introduces a new method for risk-sensitive investment management using RL.

Sharp bounds on binary model inference performance.