Reinsurance can help life insurers maintain higher capital guarantees without losing utility.
problem Decreasing capital guarantees in life insurance products.
method Dynamic investment-reinsurance optimization problem with simultaneous Value-at-Risk and no-short-selling constraints. Introduced guarantee-equivalent utility gain for comparison.
result Optimally managed reinsurance allows insurers to offer higher capital guarantees without reducing expected utility.
End-to-end differentially private LDA using spectral algorithm with theoretical guarantees.
problem Learning LDA models with differential privacy.
method Spectral algorithm with noise injection for differential privacy, identifying subsets of edges (configurations) for privacy guarantees.
result End-to-end differentially private spectral algorithm for LDA with utility guarantees.
The paper evaluates privacy in differential privacy machine learning, finding large gaps between guarantees and practical utility.
problem Lack of understanding and control over privacy and utility trade-offs in differential privacy machine learning.
method Experiments with logistic regression and neural networks to quantify privacy impact and compare different mechanisms.
result There is a significant gap between privacy guarantees and practical utility in differential privacy machine learning.
New algorithm for privacy-preserving nonconvex optimization.
problem Privacy-preserving nonconvex empirical risk minimization.
method Differentially private stochastic gradient descent algorithm.
result Achieves strong privacy guarantees efficiently with improved utility.
The paper proposes a method to learn the structure of continuous-action games with non-parametric utilities using a limited number of samples.
problem Learning the exact structure of continuous-action games with non-parametric utility functions.
method An ℓ1 regularized method that encourages sparsity of the Fourier transform coefficients of the utility functions, accessed via a few Nash equilibria and their noisy utilities. result The method recovers the exact structure of the utility functions and the game structure with provable theoretical guarantees.
The paper presents a method to preserve privacy in text analysis using calibrated noise.
problem Accurately learning from user data while maintaining privacy.
method Calibrated multivariate perturbations applied to word embeddings to achieve geo-indistinguishability.
result The method provides better privacy guarantees than baseline models with minimal utility loss.
New method generates private synthetic data with optimal utility for smooth queries.
problem Achieving strong utility guarantees for meaningful downstream analysis of sensitive datasets.
method Proposes a polynomial-time algorithm for generating (ε,δ)-differentially private synthetic data with minimax optimal error rates for smooth queries. result Achieves a minimax error rate of Ok,d(n−min{1,dk}) for k-smooth queries, up to a log(n) factor. Proposes MIP, a privacy notion that requires less randomness than DP, leading to better utility.
problem Preserving privacy in machine learning models with sensitive data.
method Introduces membership inference privacy (MIP) as a new privacy notion and shows its relationship with differential privacy (DP).
result MIP can be achieved with less randomness than DP, resulting in better utility.
Gradient noise improves privacy-protected optimization performance.
problem Improving privacy in convex optimization while maintaining utility.
method We analyze the effect of gradient perturbation on differentially private convex optimization, focusing on expected curvature.
result Gradient perturbation can achieve a significantly improved utility guarantee for differentially private convex optimization.
We consider a discrete-time financial market model with finite time horizon and give conditions which guarantee the existence of an optimal strategy for the problem of maximizing expected terminal utility. Equivalent martingale measures are constructed using optimal strategies.
KNG mechanism provides sanitized statistical summaries with strong privacy and utility guarantees.
problem Producing sanitized statistical summaries with differential privacy.
method Promotes summaries that minimize an objective function by weighting gradients, achieving utility similar to objective perturbation but with stronger privacy guarantees.
result KNG's noise is asymptotically negligible compared to statistical error for many problems.
Differentially private fair binary classification algorithm developed.
problem Balancing privacy and fairness in binary classification.
method Decoupling technique for fairness, refinement for differential privacy.
result Algorithm maintains fairness, privacy, and utility guarantees.
New framework for fair ranking with noisy protected attributes.
problem Errors in socially-salient attributes undermine fairness guarantees.
method Modeling perturbations in protected attributes and incorporating probabilistic information.
result Framework provides provable guarantees on fairness and utility.
LDP is equivalent to contraction of E_γ-divergence, impacting privacy and utility.
problem Analyzing trade-offs between privacy and utility in estimation problems.
method Equivalence of LDP constraints to contraction coefficients of E_γ-divergence, using f-divergences and estimation-theoretic tools.
result LDP guarantees can be expressed in terms of contraction coefficients of arbitrary f-divergences.
The paper optimizes pension policies with guarantees and sustainability constraints.
problem Designing optimal pension policies with guarantees and sustainability constraints.
method Dynamic utility model, stochastic domain, overlapping generations, time-consistent decision criterion.
result Optimal investment/pension policy computed for a general framework.
Paper improves privacy in machine learning optimization.
problem Efficiently private empirical risk minimization for smooth objectives.
method Gradient descent with output perturbation for strongly convex objectives; RRPSGD for non-convex objectives.
result Proves improved utility and running time for private optimization.
This paper tackles robust control of noisy systems with uncertain distributions.
problem Optimal control of sampled-data stochastic systems with multiplicative noise and distributional ambiguity.
method Develops a convex relaxation to handle the ``concave-max'' geometry and derives a probabilistic performance guarantee.
result Derives an explicit, non-asymptotic bound on the duality gap and proves robust viability conditions.
New guarantees for adaptive combinatorial maximization with various objectives.
problem Maximizing under cardinality constraints and minimum cost coverage in adaptive settings.
method Bayesian approach with comprehensive approximation guarantees for various utility functions.
result Maximal gain ratio is a new parameter that provides stronger approximation guarantees than greedy policies.
This work improves algorithm design for structured Pfaffian settings.
problem Designing algorithms for specific application domains with theoretical guarantees.
method Data-driven algorithm design using hyperparameter tuning and learning guarantees.
result Introduced the Pfaffian GJ framework for providing learning guarantees for Pfaffian function classes.
DP-ADMM provides differential privacy for ADMM-based distributed learning.
problem Privacy concerns in ADMM-based distributed machine learning.
method Combines approximate augmented Lagrangian function with time-varying Gaussian noise addition.
result Achieves higher utility for general objective functions under the same differential privacy guarantee.
The paper examines utility maximization in markets with hidden Gaussian drift, finding restrictions on model parameters.
problem Utility maximization problems in markets with hidden Gaussian drift mean-reverting processes.
method Derives sufficient conditions for bounded maximum expected utility of terminal wealth for models with full and partial information.
result Restrictions on model parameters for bounded maximum expected utility.
The paper tackles statistical and computational challenges in learning correlated reward models.
problem The Independence of Irrelevant Alternatives (IIA) assumption collapses human preferences into a universal utility function, leading to coarse approximations.
method The paper investigates the statistical and computational challenges of learning a correlated probit model using best-of-three preference data.
result Best-of-three preference data overcomes the limitations of pairwise preference data, allowing for more fine-grained modeling of human preferences.
New algorithm for reinforcement learning reduces complexity and guarantees convergence.
problem Reinforcement learning problems with convex occupancy measures.
method MD-CURL, inspired by mirror descent, uses non-standard regularization.
result Achieves convergence guarantees and simple closed-form solution.
Proposes element-level differential privacy for better privacy and utility in statistical learning.
problem Challenges of strong differential privacy in statistical learning applications.
method Introduces element-level differential privacy, extending classical DP to protect specific user elements.
result Provides better utility and more robust results compared to classical DP by allowing finer privacy protections.
Insurance companies often include very long-term guarantees in participating life insurance products, which can turn out to be very valuable. Under a guaranteed annuity options (G.A.O), the insurer guarantees to convert a policyholder's accumulated funds to a life annuity at a fixed rated when the policy matures. Both …
Paper relaxes differential privacy for correlated features, improving privacy-utility trade-off.
problem Standard differential privacy ignores feature correlation, leading to suboptimal privacy-utility balance.
method Introduces CorrDP framework that accounts for feature correlation, using total variation distance for quantification.
result CorrDP algorithms outperform standard DP in synthetic and real-world datasets with insensitive features.
This paper investigates the problem of maximizing expected terminal utility in a (generically incomplete) discrete-time financial market model with finite time horizon. In contrast to the standard setting, a possibly non-concave utility function U is considered, with domain of definition R. Simple conditio…
Bayesian optimization method for privacy-utility trade-off.
problem Quantifying privacy-utility trade-off for complex machine learning tasks.
method Bayesian optimization methodology for empirical utility measurement.
result Efficiently characterizes privacy-utility trade-off for differentially private algorithms.
New algorithm tackles unknown utility network resource allocation.
problem Maximizing network utility with unknown agent utilities.
method Modeling as a bandit problem, proposing algorithms for resource allocation.
result Proposed algorithms are optimal when all agents have the same utility.
A new method for unlearning trained models without needing the original data.
problem Lack of access to original training data for privacy-preserving unlearning.
method Uses a surrogate dataset to approximate statistical properties and calibrates noise based on statistical distance.
result Effective unlearning of trained models with strong privacy guarantees, even without access to the original data.
Paper improves privacy and utility of SGD with bounded domain and smooth losses.
problem Lack of tight privacy bounds and practical assumptions in DPSGD.
method Rigorous privacy characterization for DPSGD with general L-smooth and non-convex loss functions, tracking privacy loss over iterations.
result Privacy loss converges without convexity assumption for bounded domain, improving utility.
Proposes a new framework for optimizing utility with state-dependent benchmarks.
problem Various interpretations of benchmarks in utility functions.
method General framework of state-dependent utility optimization with stochastic benchmarks.
result Provides optimal solutions and addresses issues of well-definedness and feasibility.
Enhanced privacy, utility, and efficiency through MUST subsampling.
problem Balancing privacy, utility, and computational efficiency in data analysis.
method MUltistage Sampling Technique (MUST) for privacy amplification in differential privacy.
result MUST offers stronger privacy guarantees (ϵ) than one-stage subsampling methods while maintaining similar utility and computational efficiency. A new learning-to-rank approach ensures fairness for item providers in dynamic ranking systems.
problem Myopically optimizing user utility can be unfair to item providers in two-sided markets.
method A controller that integrates unbiased estimators for fairness and utility, dynamically adapting as more data becomes available.
result Empirically, the algorithm is highly practical and robust, ensuring amortized group fairness.
The paper analyzes and improves privacy in machine learning through importance sampling.
problem Ensuring privacy in machine learning while maintaining utility and efficiency.
method Individualized privacy analysis of importance sampling, proposing two approaches for constructing sampling distributions.
result Proposed approaches optimize privacy-efficiency trade-off and outperform uniform sampling.
This work provides statistical guarantees for VAEs using PAC-Bayesian theory.
problem Theoretical properties of VAEs remain open questions.
method PAC-Bayesian theory to derive statistical guarantees.
result Upper bounds on Wasserstein distance between input and generative model.
New algorithm maintains privacy while improving model performance in selective release.
problem Privacy degradation and slow convergence in DPSGD.
method Differentially Private Selective Release based on Clipped Gradients (DPSR-CG).
result Maintains strict privacy guarantees while achieving exceptional model performance.
DP-LSSGD improves privacy-preserving ML models by smoothing out noise.
problem Privacy-preserving ML models have lower utility than non-private ones.
method DP-LSSGD uses Laplacian smoothing to improve utility of DP-SGD.
result DP-LSSGD achieves the same DP guarantee as DP-SGD but with better stability and generalization.
This work proposes a new pre-processing method for supervised learning to improve fairness without sacrificing utility.
problem Improving fairness in supervised learning without compromising model performance.
method Task-tailored pre-processing approach that balances fairness and utility.
result The proposed method preserves consistent trade-offs among multiple downstream models and improves fairness in computer vision tasks.
A scalable protocol for federated averaging with privacy and correctness guarantees.
problem Privacy and correctness in federated learning from multiple parties.
method Scalable protocol using correlated and independent Gaussian noise, analyzed for differential privacy and graph topology.
result Nearly matches trusted curator model's utility with minimal communication.
Improved privacy and utility in machine learning with adaptive differential privacy.
problem Enhancing privacy in machine learning models while maintaining utility.
method Adaptive differentially private (ADP) learning method that optimally adapts noise to stepsize.
result ADP method significantly improves utility compared to standard differentially private methods.
Extends risk control to adaptive data collection, anytime-valid guarantees.
problem Ensuring safety of machine learning models with critical risk measures.
method Sequential risk controlling prediction sets (RCPS) for adaptive data collection and active labeling.
result Anytime-valid guarantees for risk control in sequential data collection.
Enhanced stability improves privacy in machine learning.
problem Improving privacy in machine learning training while maintaining accuracy.
method Study of stability in private empirical risk minimization, focusing on strongly-convex loss functions and uniform stability.
result An algorithm with uniform stability of β implies a bound of O(√β) on the scale of noise required for differential privacy.
Study optimal investment-reinsurance strategies in equity-linked insurance products using Stackelberg game theory.
problem Optimizing investment and reinsurance strategies in equity-linked insurance products with capital guarantees.
method Modelled as a Stackelberg game where reinsurer acts as leader and insurer as follower, with general utility functions and power utility functions analyzed.
result Derive Stackelberg equilibrium for general utility functions and calculate it explicitly for power utility functions, finding reinsurer optimizes premium to incentivize maximal reinsurance purchase.
Paper tackles robust MDPs with sample complexity guarantees.
problem Learning safe policies in uncertain environments.
method Introduces augmented state space and RCVI algorithm.
result First sample complexity guarantee for RCMDPs.
Paper improves privacy-utility trade-off in federated learning.
problem Repeated parameter sharing in federated learning leaks private data.
method Proposes a new representation federated learning objective with differential privacy guarantees.
result Algorithm \DPFEDREP\ converges to a global optimal solution with a linear rate and privacy budget-dependent radius.
Proactive DP optimizes privacy and utility in DP-SGD with a fixed privacy budget.
problem Balancing privacy and utility in differential privacy for machine learning.
method Proposes a pro-active DP framework that allows a-priori selection of DP-SGD parameters to maximize test accuracy.
result Proactive DP can optimize utility of DP-SGD with a fixed privacy budget (ε, δ).
Efficiently approximates fairness-accuracy trade-offs for diverse datasets.
problem Inherent trade-off between fairness and accuracy in machine learning models.
method You-Only-Train-Once (YOTO) framework for computationally efficient approximation.
result Robust methodology for auditing model fairness with statistical guarantees.