Study gap-dependent regret bounds for risk-sensitive RL.
problem Risk-sensitive reinforcement learning with entropic risk measure.
method Propose cascaded gaps to adapt to problem structures, derive regret bounds.
result Exponential improvement over existing bounds in appropriate settings.
New methods reduce bias in estimating optimality gaps for risk-averse stochastic programs.
problem Optimality gap estimation bias in risk-averse stochastic programs.
method Two independent samples, each estimating a different component of the optimality gap.
result Our method reduces bias in estimating optimality gaps for risk-averse problems.
Although not a formal pricing consideration, gap risk or hedging errors are the norm of derivatives businesses. Starting with the gap risk during a margin period of risk of a repurchase agreement (repo), this article extends the Black-Scholes-Merton option pricing framework by introducing a reserve capital approach to …
Improves Bayesian predictive performance in misspecified models.
problem Misspecification gap between inferential and predictive risks.
method Develops a multi-sample loss (PACm) to bridge the gap. result Empirical study shows improved predictive distribution.
Reply to Tetlock et al. on tail risk and probability gap.
problem Expert judgment fails to account for tail risk.
method Comparison of forecasting tournaments and extreme value theory.
result Greater gap between tail expectation and probability properties.
Investigates optimal PPI strategies in jump-diffusion models to mitigate downside risk.
problem Gap risk in PPI strategies due to jumps in asset price dynamics.
method Optimization problem with S-shaped utility functions, solved via martingale approach in a jump-diffusion framework.
result Determines optimal PPI strategy to maximize expected utility of terminal wealth.
Study reveals a hidden cost in derivatives markets through option-implied discount factors.
problem The hidden cost in derivatives markets, not visible in price space.
method Minute-level NBBO data on options, reduced-form specification linking carry gap to implementation risk, trading frictions, and financial conditions.
result An annualized carry gap exists, linked to implementation risk and financial conditions.
Extends portfolio optimization with two quasiconvex risk measures.
problem Optimizing portfolios with dual risk measures for multiple stakeholders.
method Dual problem formulation, bisection algorithm, duality results.
result Approximately optimal solutions can be achieved with prescribed optimality gap.
Adversarial training leads to large generalization gap, decomposed into bias and variance.
problem Understanding the large generalization gap in adversarially trained models.
method Bias-Variance decomposition of test risk as a function of adversarial perturbation radius.
result Bias increases monotonically with adversarial perturbation radius and is dominant in test risk.
Improved risk-sensitive RL with exponential Bellman equation and better regret bounds.
problem Exponential gap between upper and lower bounds in risk-sensitive RL.
method Identified and addressed deficiencies in existing algorithms and analysis; developed novel analysis and exploration mechanism.
result Improved regret upper bounds over existing ones.
The paper explores the information-theoretic nature of excess risk in machine learning.
problem Understanding the excess risk in machine learning models.
method Formulates the minimax excess risk as a zero-sum game and modifies it to allow swapping of the order of play.
result Proves that under certain conditions, the duality gap is zero, allowing for the application of Bayesian results to provide bounds on minimax excess risk.
Study shows cooperation can reduce investment risk and price gaps.
problem Investment risk and price gaps in cooperative markets.
method Introduced Collective Arbitrage and Collective Super-replication, established asset pricing theorems.
result Reduction of price intervals through collective super-replication.
The paper proves how Transformers learn from context and generalize well.
problem Understanding how Transformers generalize from diverse tasks.
method Developed a statistical theory for in-context learning, separating risk into Bayes Gap and Posterior Variance.
result The Posterior Variance is task-independent, and the Bayes Gap decreases with more in-context examples.
Digitwashing gap boosts stock crash risk, study finds.
problem The gap between companies' digital promises and actual performance increases stock crash risk.
method Empirical analysis of Shanghai and Shenzhen A-share companies from 2010 to 2021, robustness tests conducted.
result GDT significantly increases stock price crash risk, confirmed by robust tests.
The paper analyzes risk bounds and Rademacher complexity in batch RL.
problem Estimating/minimizing Bellman error with general value function approximation.
method Characterizes generalization performance using Rademacher complexities of function classes.
result Risk bounds and Rademacher complexities provide insights into batch RL.
Paper explores PG for MCR, finding suboptimal policies but providing bounds.
problem Optimizing coherent risk in MDPs using PG.
method Developed practical PG implementation using state distribution reweighting.
result PG can learn risk-sensitive policies but suboptimality is common.
Two new algorithms solve privacy-constrained SVI and SSP problems.
problem Privacy-constrained stochastic variational inequality and saddle-point problems.
method Proposed Noisy Stochastic Extragradient (NSEG) and Noisy Inexact Stochastic Proximal Point (NISPP) algorithms.
result Optimal risk bounds for weak gap function with sampling with replacement.
New bound limits generalization gap for large models, independent of model complexity.
problem Understanding generalization gap in large-scale machine learning models.
method Established a model-independent upper bound for generalization gap using Rényi entropy.
result Generalization gap can be maintained with arbitrarily large models if data entropy is sufficient.
CCPs, Central Clearing, CSA, Credit Collateral and Funding Costs Valuation FAQ: Re-hypothecation, CVA, Closeout, Netting, WWR, Gap-Risk, Initial and Variation Margins, Multiple Discount Curves, FVA?q-fin.PR We present a dialogue on Funding Costs and Counterparty Credit Risk modeling, inclusive of collateral, wrong way risk, gap risk and possible Central Clearing implementation through CCPs. This framework is important following the fact that derivatives valuation and risk analysis has moved from exotic derivatives managed…
Counterparty Risk FAQ: Credit VaR, PFE, CVA, DVA, Closeout, Netting, Collateral, Re-hypothecation, WWR, Basel, Funding, CCDS and Margin Lendingq-fin.PR We present a dialogue on Counterparty Credit Risk touching on Credit Value at Risk (Credit VaR), Potential Future Exposure (PFE), Expected Exposure (EE), Expected Positive Exposure (EPE), Credit Valuation Adjustment (CVA), Debit Valuation Adjustment (DVA), DVA Hedging, Closeout conventions, Netting clauses, Collateral …
LLM sandbox and persona dynamics create unethical reality gaps that shift risk to users.
problem Ethical issues arise from LLMs generating reality gaps that shift risk to uninformed users.
method Analyzes the ethical implications of LLM sandbox and persona dynamics, comparing them to financial regulation and compliance.
result Active generation of reality gaps is unethical as it shifts epistemic risk to users.
Several recently proposed architectures of neural networks such as ResNeXt, Inception, Xception, SqueezeNet and Wide ResNet are based on the designing idea of having multiple branches and have demonstrated improved performance in many applications. We show that one cause for such success is due to the fact that the mul…
This paper introduces modal epistemic tools for risk management.
problem Identifying and certifying risk claims when institutions lack the necessary epistemic stance.
method Develops crisp and fuzzy modal semantics for assurance and working commitment, distinguishing between object-level risk claims and meta-level epistemic diagnostics.
result Risk governance should model evidential incompleteness and failures of escalation, not just hazards and losses.
We propose a model for the credit and liquidity risks faced by clearing members of Central Counterparty Clearing houses (CCPs). This model aims to capture the features of: gap risk; feedback between clearing member default, market volatility and margining requirements; the different risks faced by various types of mark…
Data augmentation has been widely applied as an effective methodology to improve generalization in particular when training deep neural networks. Recently, researchers proposed a few intensive data augmentation techniques, which indeed improved accuracy, yet we notice that these methods augment data have also caused a …
This work analyzes generalization in federated learning using information theory.
problem Generalization performance in federated learning is less explored compared to centralized learning.
method The work applies an information-theoretic analysis via the conditional mutual information (CMI) framework to study federated learning's two-level generalization.
result The work derives multiple CMI-based bounds, including hypothesis-based CMI bounds and fast-rate evaluated CMI bounds, which improve convergence rates for specific model aggregation strategies and structured loss functions.
Optimizes regret distribution in stochastic bandits for risk balance.
problem Balancing regret expectation and tail risk in stochastic bandits.
method Characterizes optimal regret tail probability for any threshold, proposes new policies.
result Discovers an intrinsic gap in optimal tail rate based on time horizon uncertainty.
A new reinforcement learning framework separates users into risk-tolerant and risk-averse groups for better performance.
problem Improving performance for risk-averse users in reinforcement learning.
method Introducing a tiered reinforcement learning approach with two policies: πextO and πextE. result Achieving constant regret for risk-averse users, independent of the number of episodes.
Research proposes a model to estimate transaction costs and assess asset liquidity risk.
problem Lack of standardized models for asset liquidity risk in asset management.
method Develops a market impact model and a two-regime model based on power-law property.
result Defines liquidity measures and applies model to stocks and bonds.
Paper explores generalization of minimax learners, proposing a new metric.
problem Understanding how minimax learners perform on unseen data.
method Proposes a new metric, the primal gap, to study generalization of minimax learners.
result Derives generalization error bounds for the primal gap in nonconvex-concave settings.
TRACE analyzes risk changes in models trained on shifted data.
problem Understanding performance changes when a model trained on shifted data is used.
method TRACE framework decomposes risk change into four factors: generalization gaps, model change penalty, and covariate shift penalty.
result TRACE provides a diagnostic tool to understand and quantify risk changes due to covariate shift.
MVPI framework optimizes risk in reinforcement learning, improving performance in robot simulations.
problem Optimizing risk in reinforcement learning control problems.
method Mean-Variance Policy Iteration (MVPI) framework for risk-averse control in MDPs.
result Risk-averse TD3 outperforms previous methods in robot simulation tasks.
Paper introduces Lambda EVaR, a new risk measure.
problem Risk management, especially in finance.
method Lambda extension of Rényi entropic value-at-risk (Λ-EVaR). Defines properties and provides axiomatic characterization.
result Λ-EVaR bridges adaptive risk tolerance and moment-sensitive risk assessment.
Improves reinforcement learning policies for robustness.
problem Lack of robustness in reinforcement learning policies.
method Risk-aware Distributional Reinforcement Learning (SDPG) with CVaR.
result Risk-averse policies achieve robustness against disturbances.
Study uses CNN to analyze images of SMEs for bankruptcy risk.
problem Lack of data for risk analysis of SMEs.
method Created images for each SME, trained CNN on these images.
result CNN achieved 97.8% accuracy in predicting bankruptcy.
Improved sample complexity for identifying best policies in risk-sensitive reinforcement learning.
problem Identifying approximately optimal policies in risk-sensitive reinforcement learning with exponential horizon dependence.
method Forward-model based algorithm with KL-based exploration bonuses adapted for entropic criterion, leveraging smoothness properties of exponential utility and a new stopping rule.
result Achieved sample complexity matching the lower bound, closing the gap between upper and lower bounds.
Research creates a taxonomy to bridge AI security and regulatory gaps.
problem Disciplinary disconnect between technical and legal teams in AI risk assessment.
method Developed an AI System Threat Vector Taxonomy with 9 domains and 53 sub-threats.
result Empirically validated and aligned with ISO/IEC 42001 controls and NIST AI RMF functions.
New concept of partial law invariance connects decision theory and financial risk management.
problem Connecting decision theory and financial risk management under uncertainty.
method Characterizing partially law-invariant coherent risk measures via a novel representation formula.
result Strong partial law invariance bridges the gap between existing risk measure representations.
Despite the fact that the Euler allocation principle has been adopted by many financial institutions for their internal capital allocation process, a comprehensive description of Euler allocation seems still to be missing. We try to fill this gap by presenting the theoretical background as well as practical aspects. In…
New measure quantifies function similarity for optimization.
problem Measuring similarity between functions for optimization.
method Quantifies sub-optimality gaps and operation rules.
result Unified measure for various functional similarities.
Develops a Bonus-Malus model for cyber risk insurance to incentivize cybersecurity.
problem Lack of effective insurance strategies to incentivize cybersecurity.
method Proposes a Bonus-Malus model and a mathematical model with a numerical algorithm.
result Demonstrates how a Bonus-Malus system resolves moral hazard and benefits the insurer.
Study risk bounds for distributed ERM with general loss functions and hypothesis spaces.
problem Limited theoretical analysis for distributed ERM with general loss functions and hypothesis spaces.
method Derive tight risk bounds under assumptions on hypothesis space and loss function.
result Developed more general risk bound for distributed ERM without strong convexity restriction.
Develops uniform convergence guarantees for a broad class of risk functionals in supervised learning.
problem Bounding generalization gaps for various risk functionals beyond the expectation.
method Establishes uniform convergence for Hölder risk functionals, providing guarantees for empirical risk minimization.
result First uniform convergence results for estimating the CDF of loss distributions, applicable to various risk functionals.
New bounds show faster convergence for learning algorithms.
problem Improving risk bounds for learning algorithms.
method Using algorithmic stability and common assumptions like Polyak-Lojasiewicz condition, smoothness, and Lipschitz continuity.
result Achieves convergence rate of O(log2(n)/n2) with high probability. CCI combines Bayesian and gradient boosting to create fair, reliable credit risk scores.
problem Tackles high-stakes lending decisions with changing data distributions and fairness constraints.
method Combines Bayesian neural risk scorer and fairness-constrained gradient boosting with shift-aware fusion.
result CCI achieves best trade-off between discrimination, calibration, stability, and fairness.
Myopic optimization outperforms reinforcement learning in portfolio management, leading to lower returns and higher risks.
problem Reinforcement learning strategies in portfolio management yield lower or negative returns and higher risks compared to myopic optimization.
method Modeling execution/liquidation frictions with mark-to-market accounting, using Malliavin calculus to derive policy gradients and risk shadow price, and quantifying phantom profit.
result Myopic optimization outperforms reinforcement learning in portfolio management, leading to better returns and lower risks.
Audit shows risk claims from distributional reinforcement learning agents are often false.
problem Evaluating the risk claims made by distributional reinforcement learning agents.
method Combines a decision-relevant screening metric, ground truth from Monte Carlo, and statistical methods to audit risk claims.
result 40-95% of the strongest risk claims are refuted, indicating the learned risk reflects a training artifact rather than environment stochasticity.
Extracurricular learning closes the accuracy gap in knowledge distillation.
problem Accuracy gap between teacher and student models after knowledge distillation.
method Modeling student and teacher output distributions, sampling from an extended data distribution, and matching over this set.
result Extracurricular learning reduces the accuracy gap by 46% to 68%.