Paper finds robust Λ-quantiles equal to extremal distributions.
problem Investigating robust models for Λ-quantiles with partial loss information. method Extending classical quantiles using Λ-quantiles and applying results from robust quantiles. result Robust Λ-quantiles equal to Λ-quantiles of extremal distributions. Solves risk minimization problem with SSD constraints.
problem Finding SSD-minimal quantile function under mixed constraints.
method Explicitly works out SSD-minimal solution and relates to Skorokhod problem.
result Explicit solution to risk minimizing problem.
Proposes a non-crossing deep neural network quantile regression method.
problem Quantile crossing in nonparametric quantile regression.
method Non-crossing constraints via rectified linear unit penalty function.
result Established non-asymptotic upper bounds for excess risk.
Study quantile reward identification with 1-bit feedback constraints.
problem Best arm identification with quantile reward and 1-bit communication.
method Proposes an algorithm using noisy binary search for quantile reward estimation.
result Derives upper and lower bounds on sample complexity for 1-bit feedback.
This work connects Cramér distance to QR-DQN for DRL.
problem Improving performance in DRL by capturing full distribution of returns.
method Proves Cramér distance's equivalence to 1-Wasserstein distance and proposes a low-complexity algorithm to compute Cramér distance.
result Cramér distance and quantile regression losses yield collinear gradients under non-crossing constraints.
Investigates methods to regularize quantile regression for accurate predictions.
problem Improving accuracy and fairness in quantile regression predictions.
method Various regularization techniques including expected pinball loss, monotonicity constraints, and rate constraints.
result Deep lattice networks can maintain non-crossing quantiles and improve calibration and fairness.
Proposes a deep learning method to ensure non-crossing quantiles in conditional distributions.
problem Non-crossing quantiles issue in deep learning QR models.
method Generic deep learning algorithm enforcing quantile monotonicity.
result Ensures non-crossing quantiles up to machine precision.
Optimal wind farm placement using quantile constraints for better power output.
problem Optimizing wind farm placement to maximize power output considering spatial and temporal wind speed correlations.
method Used a probabilistic neural network with ReLU activation functions to reformulate constraints as linear ones, embedding them into a two-stage stochastic optimization problem.
result The constraint learning approach outperforms classical methods, especially for risk-averse investors.
New method for robustly interpreting ML models using quantile constraints and Wasserstein projections.
problem Assessing robustness of black-box models to input misspecification.
method Quantile-constrained Wasserstein projections for robust interpretability.
result Analytical solution for perturbation problem and smooth perturbations.
CPP solves chance constrained optimization problems with a framework that combines samples and quantile lemma.
problem Chance constrained optimization problems with constraints on random variables.
method CPP framework using samples and quantile lemma to transform into deterministic problem.
result CPP provides a posteriori guarantees on constraint satisfaction and can handle different types of chance constraints.
iQRA improves probabilistic forecasts of electricity prices.
problem Lack of uncertainty estimates in machine learning forecasts for volatile markets.
method Isotonic Quantile Regression Averaging (iQRA) with stochastic order constraints.
result iQRA outperforms state-of-the-art methods in reliability and sharpness.
Quantum algorithm samples from SDEs using DQCs and quantile mechanics.
problem Sampling from solutions of stochastic differential equations.
method Differentiable quantum circuits (DQCs) encoding latent variables, quantile mechanics.
result Quantum algorithm generates time-series from SDEs.
Investment strategy for DC pension plan with inflation risk and tail VaR constraint.
problem Maximizing terminal wealth for pension member with tail VaR constraint.
method Lagrange method and quantile optimization techniques.
result Optimal investment strategy and output in closed-form derived.
A new method improves quantile regression for high-dimensional data.
problem Handling heteroscedastic, multimodal, or skewed data in quantile regression.
method Dynamic prototypes-based probability density estimation with conformalized high-density quantile regression.
result Enhanced prediction regions with valid coverage guarantees and scalability to higher dimensions.
The issue of constructing a risk minimizing hedge under an additional almost-surely type constraint on the shortfall profile is examined. Several classical risk minimizing problems are adapted to the new setting and solved. In particular, the bankruptcy threat of optimal strategies appearing in the classical risk minim…
Uncertainty analysis in the form of probabilistic forecasting can provide significant improvements in decision-making processes in the smart power grid for better integrating renewable energies such as wind. Whereas point forecasting provides a single expected value, probabilistic forecasts provide more information in …
We relax demographic parity in regression by enforcing parity at quantile levels and score thresholds.
problem Enforcing full distributional fairness in regression can lead to substantial accuracy loss.
method Introduce (ℓ, Z)-fair predictor, derive closed-form solutions, and develop post-processing algorithm. result The risk gap to the continuous optimum vanishes as the grid is refined, and we enable targeted fairness corrections.
RQR improves prediction intervals for skewed data.
problem Invalid prediction intervals for skewed noise.
method Relaxed Quantile Regression (RQR) for asymmetric noise.
result Improved prediction intervals with desirable qualities.
Paper proposes a federated learning method for quantile inference with local differential privacy.
problem Federated learning of quantile inference under local differential privacy constraints.
method Local stochastic gradient descent with randomized mechanism for privacy and efficiency.
result Asymptotic normality and functional central limit theorem for the proposed estimator.
New KQEs improve probability metrics without mean function constraints.
problem Improving probability metrics without relying on mean function representations.
method Kernel quantile embeddings (KQEs) to construct new distances.
result KQEs offer a competitive alternative to MMD with near-linear cost.
Paper tackles hard shape constraints in kernel machines.
problem Enforcing shape requirements in a hard fashion is challenging.
method Tightened second-order cone constrained reformulation for kernel machines.
result Performance guarantees and efficiency demonstrated in various applications.
Optimizes quantile and semi-adversarial regret with novel root-logarithmic regularizers.
problem Minimizes regret in adversarial and semi-adversarial online learning.
method FTRL with root-logarithmic regularizers for quantile and semi-adversarial settings.
result Achieves minimax optimal regret bounds in both paradigms.
Locally private online quantile regression method addresses privacy constraints.
problem Estimating and inferring quantile regression under local differential privacy constraints.
method Developed a finite-alphabet channel where users compute local contributions, apply randomized response, and send reports. A public decoder corrects distortion and reconstructs inputs for averaging.
result Established local privacy, decoder unbiasedness, consistency, asymptotic normality, and inference for scalar contrasts.
A new method calculates risk loadings in classification ratemaking without subjective parameters.
problem Subjective risk loading parameters in classification ratemaking.
method Bootstrap method to calculate total risk premium, then determine risk loading parameters using quantile regression models.
result Risk premiums calculated by the new method reasonably differentiate different risk classes.
Novel method for efficient optimization of noisy, expensive hybrid models.
problem Efficient optimization of hybrid models with noisy observations and constraints.
method Constrained Upper Quantile Bound (CUQB) method exploiting composite structure.
result Significantly improved sampling efficiency and theoretical guarantees.
This paper solves robust utility maximization with unknown claim dependencies.
problem Investor optimizes utility in the presence of an intractable contingent claim.
method Quantile optimization approach, transforming dynamic problem into static concave optimization.
result Optimal payoffs depend on ambiguity attitude, market conditions, and claim characteristics.
Bayesian method for estimating inputs leading to specific probability outputs.
problem Estimating inputs for specific probability outputs of uncertain functions.
method Bayesian strategy using Gaussian process modeling and SUR principle.
result Surpassed performance of existing methods through numerical experiments.
New federated conformal prediction method addresses label shift for uncertainty quantification.
problem Label shift in federated learning and its impact on uncertainty quantification.
method Quantile regression-based federated conformal prediction method with privacy constraints.
result Method provides valid coverage of prediction sets and differential privacy guarantees.
For an exponential utility maximizing investment strategy in a Black-Scholes Setting, fixed upper and lower constraints are introduced on the terminal wealth. This is equivalent to combining the optimal strategy with options. The resulting distribution is investigated in terms of change of quantiles. The theory is illu…
This paper studies the inference problem in quantile regression (QR) for a large sample size n but under a limited memory constraint, where the memory can only store a small batch of data of size m. A natural method is the naïve divide-and-conquer approach, which splits data into batches of size m, computes the l…
Quantile regression attacks outperform shadow models in unseen class membership inference attacks.
problem Failure of shadow model attacks on unseen classes due to limited data access.
method Quantile regression attacks that learn features of member examples.
result Quantile regression attacks achieve up to 11x higher TPR than shadow model-based approaches.
Proposes methods for online conformal prediction with nested prediction sets across multiple confidence levels.
problem Need for uncertainty quantification with multiple confidence levels in diverse applications.
method Online optimization perspective to enforce nestedness of prediction sets while controlling quantile estimation error.
result Achieves stable coverage across all levels, strictly nested prediction sets, and improved efficiency.
Develops a new method for optimizing with uncertain data.
problem Uncertainty in real-world optimization problems.
method Combines chance constraints and constraint learning for mixed-integer linear optimization.
result Data-driven solution for setting probabilistic bounds on learned constraints.
A new method avoids quantile crossing in time series forecasting.
problem Quantile crossing in joint quantile regressions.
method Incremental (Spline) Quantile Functions (I(S)QF) with neural network.
result Improves consistency and accuracy in time series forecasting.
New risk measures for quantiles under ambiguity improve risk sharing.
problem Risk optimization under ambiguity using quantiles.
method Introducing Choquet quantiles and Choquet Expected Shortfall.
result Optimal allocations for quantile agents under ambiguity.
SCQRNN prevents quantile crossing and improves computational efficiency.
problem Quantile crossing issue in regression models.
method Integrates ad hoc sorting in training to prevent quantile crossing and enhance computational efficiency.
result SCQRNN achieves faster convergence and non-intersecting quantiles.
A new method calibrates Gaussian processes for more accurate uncertainty estimates.
problem Uncertainty estimates from Gaussian processes are often miscalibrated in practice.
method A novel calibration approach using different hyperparameters to generate more accurate predictive quantiles.
result The method yields tighter predictive quantiles and is more flexible than existing approaches.
Axiomatizes Λ-quantiles, a generalization of quantiles.
problem Found an axiomatization for Λ-quantiles. method Characterized Λ-quantiles using the locality property. result Local changes in distribution do not affect Λ-quantiles. Develops a method to ensure accurate quantile forecasts across multiple levels.
problem Ensuring accurate quantile forecasts at multiple levels, even under distribution shifts.
method Multi-level quantile tracker (MultiQT) wraps around any forecaster to produce calibrated forecasts.
result Guaranteed calibration of quantile forecasts at multiple levels, even against adversarial shifts.
Proposes a method to estimate conditional quantiles using both high-fidelity and low-fidelity data.
problem Difficulty in estimating conditional quantiles with scarce high-fidelity data.
method Two-stage, model-agnostic method using local quantile link and level function estimation.
result The method yields more accurate quantile estimates and tighter prediction intervals.
Sequential quantile estimation refers to incorporating observations into quantile estimates in an incremental fashion thus furnishing an online estimate of one or more quantiles at any given point in time. Sequential quantile estimation is also known as online quantile estimation. This area is relevant to the analysis …
QR-MIX models joint state-action values as a distribution to handle randomness in MARL.
problem Randomness in rewards and observations leads to randomness in long-term returns in MARL.
method QR-MIX uses quantile regression and combines it with QMIX and IQN to model joint state-action values as a distribution.
result QR-MIX outperforms QMIX in the StarCraft Multi-Agent Challenge (SMAC) environment.
The paper proposes a method for predicting equity premium using penalized quantile regression.
problem Heteroscedasticity and heavy-tails in equity premium prediction.
method Penalized quantile regression with consistent variable selection across multiple quantiles.
result The proposed method outperforms benchmark methods and reveals interesting predictor relationships.
Supervised learning is an active research area, with numerous applications in diverse fields such as data analytics, computer vision, speech and audio processing, and image understanding. In most cases, the loss functions used in machine learning assume symmetric noise models, and seek to estimate the unknown function …
Improved conformalized quantile regression for adaptive prediction intervals.
problem Lack of adaptiveness in the conformal step of conformalized quantile regression.
method Cluster explanatory variables by permutation importance and apply k conformal steps.
result Improved prediction intervals are more adaptive to heteroscedasticity.
Smoothed SGD improves quantile estimation without crossing curves.
problem Estimating quantiles without crossing estimated curves.
method Smoothed SGD algorithm with Bahadur representation and Gaussian approximation.
result Smoothed SGD provides non-asymptotic tail probability bounds and a Gaussian approximation for quantile estimates.
In most machine learning applications, classification accuracy is not the primary metric of interest. Binary classifiers which face class imbalance are often evaluated by the Fβ score, area under the precision-recall curve, Precision at K, and more. The maximization of many of these metrics can be expressed as a con…
Private estimation of many quantiles using differential privacy.
problem Estimating quantiles of a distribution privately.
method Two approaches: 1) Private estimation of empirical quantiles, 2) Uniform density estimation.
result There is a tradeoff between estimating quantiles at specific points and uniformly estimating the quantile function.