A new method for generating SPX and VIX risk scenarios using perturbed optimal transport.
problem Generating accurate risk estimates for SPX and VIX without full recalibration.
method A joint optimal transport calibration with perturbation methodology for sensitivities, combined with Skew Stickiness Ratio dynamics.
result The proposed method produces accurate risk estimates relative to full recalibration and is computationally faster.
SVAT reduces investment risks by making stock models sensitive to adversarial perturbations.
problem Risk control in stock recommendation models is insufficient, leading to high investment losses.
method SVAT combines adversarial learning and variational perturbation generation to enhance risk awareness.
result SVAT reduces investment risks by more than 30% compared to state-of-the-art baselines.
We propose a novel framework for the differentially private ERM, input perturbation. Existing differentially private ERM implicitly assumed that the data contributors submit their private data to a database expecting that the database invokes a differentially private mechanism for publication of the learned model. In i…
Estimates risk in finance using Wasserstein distance and parametric models.
problem Assessing risk in financial models with model uncertainty.
method Parametric approach based on Wasserstein distance for convex risk functionals.
result Developed a numerical method using neural networks to estimate risk and optimal perturbations.
Paper proposes a new method for WDRO with local perturbations, achieving better accuracy.
problem Wasserstein distributionally robust optimization's theoretical understanding needs improvement.
method Develops a new approximation theorem and risk consistency results for WDRO.
result The proposed method achieves significantly higher accuracy on noisy datasets.
We study the risk premium impact in the Perturbative Black Scholes model. The Perturbative Black Scholes model, developed by Scotti, is a subjective volatility model based on the classical Black Scholes one, where the volatility used by the trader is an estimation of the market one and contains measurement errors. In t…
Differential privacy is concerned about the prediction quality while measuring the privacy impact on individuals whose information is contained in the data. We consider differentially private risk minimization problems with regularizers that induce structured sparsity. These regularizers are known to be convex but they…
The paper develops new methods to approximate ruin probabilities in a perturbed risk model.
problem Calculating exact ruin probabilities in a perturbed risk model is complex.
method Adapted Cramér-Lundberg model with Wiener process, four approximation methods.
result Four approximation methods provide high accuracy for ruin probabilities.
AMP regularization improves deep learning models by favoring flat minima.
problem Improving deep learning model generalization and avoiding overfitting.
method AMP regularization uses adversarial model perturbation to minimize a norm-bounded perturbation of the empirical risk.
result AMP regularization leads to state-of-the-art performance across various deep architectures.
Study enhances robustness of In-CVaR based regression models under perturbation and contamination.
problem Enhancing robustness of nonlinear regression models under perturbation and contamination.
method Introduces interval conditional value-at-risk (In-CVaR) and rigorously analyzes its robustness properties under both perturbation and contamination.
result The In-CVaR based estimator is qualitatively robust in terms of the Prokhorov metric if and only if the largest portion of losses is trimmed.
PAC-Bayesian bounds estimate adversarial robustness.
problem Estimating robustness to imperceptible input perturbations.
method PAC-Bayesian framework for averaging over hypotheses.
result General bounds valid for any type of adversarial attacks.
New framework robustly handles outliers in Wasserstein DRO for better decision-making.
problem Non-geometric perturbations like adversarial outliers distort Wasserstein distance.
method Proposes an outlier-robust WDRO framework using a robust Wasserstein ball.
result Derives minimax optimal excess risk bounds for robust WDRO.
New approach to adversarial robustness with non-uniform perturbations.
problem Real-world adversaries craft adversarial examples with non-uniform perturbations.
method Proposes non-uniform perturbations based on feature dependencies and data distribution.
result Shows improved robustness to real-world attacks compared to uniform perturbations.
Paper introduces input perturbation for privacy in machine learning models.
problem Protecting both training data and model parameters while maintaining privacy.
method Add noise to training data and train with perturbed data for differential privacy.
result Achieves (ε,δ)-differential privacy on the final model with privacy on original data.
Optimal reinsurance strategy found to minimize financial risk.
problem Minimizing financial risk in insurance companies through optimal reinsurance.
method Solving the problem via neural networks and a Cramér-Lundberg model.
result Optimal reinsurance strategy found to control terminal wealth and ruin probability.
Robust risk minimisation has several advantages: it has been studied with regards to improving the generalisation properties of models and robustness to adversarial perturbation. We bound the distributionally robust risk for a model class rich enough to include deep neural networks by a regularised empirical risk invol…
New method estimates model risk without knowing function class.
problem Evaluating model risk for complex, opaque models.
method Wild refitting with Bregman losses and randomized symmetrization.
result Valid upper bound on excess risk for opaque models.
New method improves solving combinatorial optimization problems with smoothed policies.
problem Solving combinatorial optimization problems repeatedly with varying instances.
method Smoothed policies with controlled random perturbations to linear oracle, leading to differentiable surrogate risk.
result Generalization bound decomposes excess risk into bias, estimation, and optimization components.
The paper bounds payoffs and option prices in discrete models.
problem Measuring risk in discrete models and incomplete markets.
method Analytical and simulated bounds for payoff functions and option prices.
result Analytical and simulated bounds for European and American options.
Study tail risk aggregation under dependence uncertainty.
problem Risk aggregation under dependence uncertainty and hidden dependence.
method Introduce hidden dependence, show compatibility with small perturbations, quantify portfolio risk.
result Small deviations in dependence structure can lead to significant risk underestimation.
We study adversarial perturbations when the instances are uniformly distributed over {0,1}n. We study both "inherent" bounds that apply to any problem and any classifier for such a problem as well as bounds that apply to specific problems and specific hypothesis classes. As the current literature contains multiple…
New method refines model-free evaluation of complex machine learning models.
problem Evaluating the excess risk of opaque machine learning predictors.
method Perturbing derivatives to create pseudo-outcomes and refitting the model twice.
result Upper bound on excess risk derived efficiently without prior function class knowledge.
Beyond existing multi-view clustering, this paper studies a more realistic clustering scenario, referred to as incomplete multi-view clustering, where a number of data instances are missing in certain views. To tackle this problem, we explore spectral perturbation theory. In this work, we show a strong link between per…
This paper explores tradeoffs between standard and adversarial risks in distributionally adversarial training.
problem Understanding the impact of adversarial training on standard risk and adversarial risk.
method Study of distributionally adversarial training with different learning settings and models.
result Derives Pareto-optimal tradeoff curves between standard and adversarial risks.
Despite achieving impressive performance, state-of-the-art classifiers remain highly vulnerable to small, imperceptible, adversarial perturbations. This vulnerability has proven empirically to be very intricate to address. In this paper, we study the phenomenon of adversarial perturbations under the assumption that the…
Neural networks are vulnerable to adversarial examples and researchers have proposed many heuristic attack and defense mechanisms. We address this problem through the principled lens of distributionally robust optimization, which guarantees performance under adversarial input perturbations. By considering a Lagrangian …
We consider a risk model where deficits after ruin are covered by a new type of reinsurance contract that provides capital injections. To allow the insurance company's survival after ruin, the reinsurer injects capital only at ruin times caused by jumps larger than a chosen retention level. Otherwise capital must be ra…
Adversarial weight perturbations can inject backdoors into trained neural models.
problem Security risk of using publicly available trained models due to backdoors.
method Extended adversarial perturbations to model weights, using a composite loss and projected gradient descent.
result Adversarial weight perturbations can be successfully injected with very small changes, exposing security risks across various tasks.
Recent works on adversarial perturbations show that there is an inherent trade-off between standard test accuracy and adversarial accuracy. Specifically, they show that no classifier can simultaneously be robust to adversarial perturbations and achieve high standard test accuracy. However, this is contrary to the stand…
We propose a categorical data synthesizer with a quantifiable disclosure risk. Our algorithm, named Perturbed Gibbs Sampler, can handle high-dimensional categorical data that are often intractable to represent as contingency tables. The algorithm extends a multiple imputation strategy for fully synthetic data by utiliz…
Adversarial training can lead to overfitting without compromising robustness.
problem Explaining benign overfitting in adversarially robust linear classification.
method Theoretical analysis and numerical experiments on adversarial training.
result Adversarially trained linear classifiers can achieve near-optimal risks despite overfitting noisy data.
Adversarial attacks can fool algorithmic trading systems.
problem Adversarial perturbations can manipulate algorithmic trading models.
method Real-time adversarial attacks on trading algorithms using universal perturbations.
result Perturbations can fool trading algorithms at unseen data points.
Proposes a stability evaluation criterion for learning models using distributional perturbations.
problem Ensuring reliable deployment of learning models in out-of-sample environments.
method Uses optimal transport discrepancy with moment constraints to quantify minimal perturbation required for model deterioration.
result Validates the practical utility of the stability evaluation criterion across various real-world applications.
Study optimal strategies for insurer's dividends, investments, and liabilities.
problem Maximize insurer's utility of dividend payments over an infinite horizon.
method Perturbation approach to obtain optimal strategy and value function in closed form.
result Obtained optimal strategy and value function for log and power utility.
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.
The process of data mining with differential privacy produces results that are affected by two types of noise: sampling noise due to data collection and privacy noise that is designed to prevent the reconstruction of sensitive information. In this paper, we consider the problem of designing confidence intervals for the…
Introduces RPU to explain randomization preference in dynamic settings.
problem Explains preference for randomization in dynamic investment problems.
method Introduces recursive perturbed utility (RPU) to incorporate randomization preference.
result Proves RPU-optimal portfolio policy is Gaussian and can be expressed in closed form.
Recent work on adversarial attack has shown that Projected Gradient Descent (PGD) Adversary is a universal first-order adversary, and the classifier adversarially trained by PGD is robust against a wide range of first-order attacks. It is worth noting that the original objective of an attack/defense model relies on a d…
Risk-averse model uncertainty framework for safe reinforcement learning.
problem Safe decision making in uncertain environments.
method Risk-averse perspective towards model uncertainty using coherent distortion risk measures; equivalent to distributionally robust safe reinforcement learning problems; efficient, model-free implementation.
result Demonstrates robust performance and safety across perturbed test environments.
As increasing amounts of sensitive personal information is aggregated into data repositories, it has become important to develop mechanisms for processing the data without revealing information about individual data instances. The differential privacy model provides a framework for the development and theoretical analy…
Neural networks have been shown to be vulnerable against minor adversarial perturbations of their inputs, especially for high dimensional data under ℓ∞ attacks. To combat this problem, techniques like adversarial training have been employed to obtain models which are robust on the training set. However, the …
New bounds for KANs trained with DP-SGD, addressing correlated noise.
problem Risk bounds for Kolmogorov-Arnold Networks trained by DP-SGD with correlated noise.
method Established new optimization and population risk analysis for KANs trained with DP-SGD, addressing correlated noise.
result First optimization and population risk analysis of correlated-noise mechanisms for DP training in non-convex settings, including neural networks.
Using integration by parts on Gaussian space we construct a Stein Unbiased Risk Estimator (SURE) for the drift of Gaussian processes using their local and occupation times. By almost-sure minimization of the SURE risk of shrinkage estimators we derive an estimation and de-noising procedure for an input signal perturbed…
Mixup improves model accuracy and calibration through data transformation and random perturbation.
problem Improving model accuracy and calibration in machine learning.
method Interprets Mixup as empirical risk minimization with data transformation and random perturbation.
result Mixup induces multiple known regularization schemes that prevent overfitting and overconfident predictions.
Proposes a method to identify critical regions in neural networks using adversarial attacks.
problem Capturing uncertainty in neural networks near decision boundaries.
method Adversarial attack method to derive uncertainty from input perturbations.
result The proposed method outperforms other uncertainty methods in capturing model uncertainty.
Optimal probability measure found for constrained stochastic processes.
problem Finding optimal probability measure with constraints for stochastic processes.
method Existence and uniqueness proof, explicit measure change, optimal drift and compensator adjustments.
result Explicit form of the optimal measure change and characterisation of adjustments.
New DP algorithm improves privacy and efficiency for convex optimization.
problem Efficient, DP algorithms for convex optimization with strong excess risk bounds.
method Output perturbation for a broad class of tilted loss functions.
result Near optimal DP excess risk and runtime bounds for convex optimization.
Paper introduces a new method for risk-sensitive investment management using RL.
problem Risk-sensitive portfolio management with unknown model parameters.
method Combines RL and risk-sensitive stochastic control with Gaussian perturbations for exploration.
result Endogenous relative-entropy regularization and optimal investment strategy derived.