arXiv research

Optimizes quantile and semi-adversarial regret with novel root-logarithmic regularizers.

We show how to reduce the process of predicting general order statistics (and the median in particular) to solving classification. The accompanying theoretical statement shows that the regret of the classifier bounds the regret of the quantile regression under a quantile loss. We also test this reduction empirically ag…

Paper studies continuous prediction with experts' advice using differential equations.

ACP-UCB1 ranks arms based on upper-tail performance, improving stochastic bandit algorithms.

AIHT improves online high-dimensional quantile regression by separating support discovery and refinement.

The paper tackles a bandit problem with infinitely many arms per group, aiming to identify the group with the highest quantile reward.

Develops a method to ensure accurate quantile forecasts across multiple levels.

Improved prediction algorithm for 'easy' sequences with reduced regret.

We propose and analyze StoROO, an algorithm for risk optimization on stochastic black-box functions derived from StoOO. Motivated by risk-averse decision making fields like agriculture, medicine, biology or finance, we do not focus on the mean payoff but on generic functionals of the return distribution. We provide a g…

Gradient equilibrium improves online learning performance without requiring sublinear regret.

We aim to design strategies for sequential decision making that adjust to the difficulty of the learning problem. We study this question both in the setting of prediction with expert advice, and for more general combinatorial decision tasks. We are not satisfied with just guaranteeing minimax regret rates, but we want …

Novel method for efficient optimization of noisy, expensive hybrid models.

The paper proposes a new policy for optimal treatment allocation based on quantile treatment effects.

Bayesian approach improves online prediction accuracy without distributional assumptions.

A robust bandit algorithm uses Dirichlet sampling to minimize regret under various distributional assumptions.

We consider a multi-armed bandit problem with covariates. Given a realization of the covariate vector, instead of targeting the treatment with highest conditional expectation, the decision maker targets the treatment which maximizes a general functional of the conditional potential outcome distribution, e.g., a conditi…

New algorithms ensure fair selection in combinatorial semi-bandit with unrestricted delays.

Proposes methods for online conformal prediction with nested prediction sets across multiple confidence levels.

Investigates methods to regularize quantile regression for accurate predictions.

A new method avoids quantile crossing in time series forecasting.

New risk measures for quantiles under ambiguity improve risk sharing.

Paper finds robust $Λ$-quantiles equal to extremal distributions.

SCQRNN prevents quantile crossing and improves computational efficiency.

Axiomatizes $Λ$-quantiles, a generalization of quantiles.

Universal algorithm learns unknown distribution for various decision-making problems.

Proposes a method to estimate conditional quantiles using both high-fidelity and low-fidelity data.

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 …

The paper proposes a method for predicting equity premium using penalized quantile regression.

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.

Proposes a deep learning method to ensure non-crossing quantiles in conditional distributions.

Smoothed SGD improves quantile estimation without crossing curves.

Private estimation of many quantiles using differential privacy.

Biased mean regression estimates factors exceeding expected loss or radiation release severity.

Bayesian method improves quantile estimation and subset selection.

New quantile methods improve uncertainty quantification across various models.

This paper analyzes quantiles of heavy-tailed distributions, separating projection direction and quantile threshold effects.

We develop a novel approach for the construction of quantile processes governing the stochastic dynamics of quantiles in continuous time. Two classes of quantile diffusions are identified: the first, which we largely focus on, features a dynamic random quantile level and allows for direct interpretation of the resultin…

ConquerNet smooths quantile regression for deep learning with minimax guarantees.

SVR analyzed within RQ framework for risk management.

Improved quantile estimation model for VaR.

We develop quantile regression models in order to derive risk margin and to evaluate capital in non-life insurance applications. By utilizing the entire range of conditional quantile functions, especially higher quantile levels, we detail how quantile regression is capable of providing an accurate estimation of risk ma…

Paper proposes a method to estimate multiple dynamic quantiles jointly.

This paper examines quantile dependence between international stock markets and evaluates its use for improving volatility forecasting. First, we analyze quantile dependence and directional predictability between the US stock market and stock markets in the UK, Germany, France and Japan. We use the cross-quantilogram, …

A new method forecasts financial tail risks by combining and weighting quantiles.

This paper is about index policies for minimizing (frequentist) regret in a stochastic multi-armed bandit model, inspired by a Bayesian view on the problem. Our main contribution is to prove that the Bayes-UCB algorithm, which relies on quantiles of posterior distributions, is asymptotically optimal when the reward dis…

IQ-BART models conditional quantiles using a non-parametric Bayesian approach.

The paper introduces a new method for forecasting financial risk using quantile-based modeling.