New method for zeroth-order stochastic gradient algorithms provides confidence intervals.
problem Lack of inferential capabilities for zeroth-order stochastic gradient algorithms.
method Established central limit theorem and provided online estimators for asymptotic covariance matrix.
result Asymptotically valid confidence sets for parameter estimation and prediction.
BCI provides calibrated prediction intervals for time series forecasts.
problem Calibration of prediction intervals for time series forecasts.
method BCI wraps around any time series forecasting models and optimizes interval lengths using dynamic programming.
result BCI achieves long-term coverage under arbitrary distribution shifts and temporal dependence.
Paper tackles online learning with interval regret, achieving adaptive bounds.
problem Non-stationary online learning over time intervals.
method Two-layer online ensemble structure with gradient variation.
result Achieves strong theoretical guarantees with adaptive bounds.
Efficient method for high confidence level inference using parallel stochastic optimization.
problem Uncertainty quantification for online estimation.
method Small number of independent multi-runs to construct t-based confidence intervals.
result Rigorous theoretical guarantee for exact coverage of confidence intervals.
Paper derives convergence rates and confidence intervals for LSA with Markovian noise.
problem Analyzing convergence rates and constructing confidence intervals for LSA with Markovian noise.
method Derives non-asymptotic Berry-Esseen bounds and multiplier block bootstrap procedure.
result Provides O(n−1/4) convergence rates and guarantees consistent inference. Stock price change in financial market occurs through transactions in analogy with diffusion in stochastic physical systems. The analysis of price changes in real markets shows that long-range correlations of price fluctuations largely depend on the number of transactions. We introduce the multiplicative stochastic mod…
Adaptive MAB algorithms handle composite, anonymous feedback without reward interval knowledge.
problem Multi-armed bandit with composite and anonymous feedback, especially without reward interval size knowledge.
method Proposed adaptive algorithms for stochastic and adversarial cases, without reward interval knowledge.
result First algorithm for adversarial case handling non-oblivious adversary and unknown reward interval size.
Optimizes liquidity provision intervals for profitable AMM participation.
problem Financial losses from poor liquidity provision intervals and reallocation costs.
method Developed a tractable stochastic optimization problem.
result Computes optimal liquidity provision intervals for profitable liquidity concentration.
New approach for handling uncertain probabilities.
problem Handling imprecise or uncertain probabilities.
method Introducing interval probability measures and updating rules.
result Formal solution to the Keynes-Ramsey controversy.
New model clusters nodes and time intervals in dynamic networks.
problem Stochastic block model's inability to account for time-varying interactions.
method Temporal partitioning, exact ICL maximization, greedy search approach.
result Exact maximization of integrated complete-data likelihood.
Develops a method for robust optimization with exact coverage confidence intervals.
problem Statistical inference and distributionally robust solutions for stochastic optimization problems.
method Generalized empirical likelihood framework based on f-divergence balls. result Provides a principled method for choosing distributional uncertainty regions for exact coverage.
Paper predicts travel costs across regions using neural networks.
problem Predicting travel costs in sparse, stochastic OD matrices.
method Recurrent Multi-Graph Neural Networks (R-MGNN) for sparse, stochastic OD matrix forecasting.
result Framework effectively predicts future OD matrices without empty elements.
Optimal learning via moderate deviations theory improves statistical accuracy.
problem Statistical estimation of expected loss in various models.
method Develops confidence intervals using moderate deviation principle.
result Proposed confidence intervals are statistically optimal.
Paper bridges statistical inference for DP-SGD, a privacy-preserving machine learning method.
problem Asymptotic statistical inference for Differentially Private Stochastic Gradient Descent (DP-SGD).
method Established asymptotic properties of SGD under randomized subsampling, extended to DP-SGD, proposed methods for constructing valid confidence intervals.
result Valid confidence intervals for DP-SGD output achieve nominal coverage rates while maintaining privacy.
RAGIC predicts stock intervals with risk considerations, improving prediction accuracy and coverage.
problem Limited success in predicting stock market outcomes due to stochastic nature and risk oversight.
method RAGIC uses a GAN with a risk module and temporal module to generate risk-sensitive stock intervals.
result RAGIC achieves a consistent 95% coverage with narrow interval widths, balancing accuracy and risk.
This paper improves offline contextual bandits using distributional robustness.
problem Improving offline contextual bandits with robustness.
method Extends Distributionally Robust Optimization (DRO) for offline contextual bandits, introducing a convex reformulation of Counterfactual Risk Minimization.
result Automatic calibration of asymptotic confidence intervals for policy optimization.
Study analyzes derivative-free loss method for solving PDEs and fluid problems.
problem Solving elliptic PDEs and fluid problems using neural networks.
method Derivative-free loss method with Feynman-Kac formulation and stochastic walkers.
result Training loss bias scales with time interval and spatial gradient, inversely with walker size.
Paper improves confidence intervals for LSA with multiplier bootstrap.
problem Improving confidence intervals for parameter estimation in LSA.
method Berry-Esseen bound for multivariate normal approximation and multiplier bootstrap.
result Valid confidence intervals for parameter estimation in LSA.
AskewSGD optimizes quantized neural networks with interval-constrained optimization.
problem Training deep neural networks with quantized weights.
method Formulates QNN training as smoothed interval-constrained optimization, proposes AskewSGD for solving each subproblem.
result AskewSGD avoids projections and allows infeasible iterates, performs better than state-of-the-art methods.
We investigate the volatility return intervals in the NYSE and FOREX markets. We explain previous empirical findings using a model based on the interacting agent hypothesis instead of the widely-used efficient market hypothesis. We derive macroscopic equations based on the microscopic herding interactions of agents and…
A new method for statistical inference using SGD under φ-mixing data.
problem Valid statistical inference for time series data with general correlation.
method Proposes a mini-batch SGD estimator and associated mini-batch bootstrap procedure for φ-mixing data. result The proposed method constructs valid confidence intervals for φ-mixing data. The paper extends conformal prediction to MDP trajectories for autonomous systems.
problem Ensuring reliability of autonomous systems by providing probabilistic guarantees.
method Applying conformal corrections to quantile regression prediction intervals.
result Conformal prediction intervals ensure the observed trajectory lies inside with high probability.
Guaranteed bounds for posterior inference in probabilistic programs.
problem Approximating the posterior distribution of probabilistic programs with provable correctness.
method Interval-based trace semantics, soundness and completeness proofs, weight-aware interval type system.
result Guaranteed bounds on the posterior distribution of probabilistic programs are computed and proven to be correct.
Cheap methods improve uncertainty in SGD solutions.
problem Uncertainty quantification in SGD solutions.
method Two resampling-based methods: parallel resampling with replacement and online resampling.
result Significantly reduced computation effort in constructing confidence intervals.
We present an empirical study of the subordination hypothesis for a stochastic time series of a stock price. The fluctuating rate of trading is identified with the stochastic variance of the stock price, as in the continuous-time random walk (CTRW) framework. The probability distribution of the stock price changes (log…
Defines a bridge process to predict financial market risks.
problem Predicting financial market risks before a default occurs.
method Defines a Brownian bridge process conditioned to zero at default.
result Leaks information about default before it happens.
Post-processes deep networks with StoNet to quantify uncertainty.
problem Uncertainty quantification in predictions from large-scale deep neural networks.
method Feeds DNN output into StoNet, trains StoNet with sparse penalty, constructs prediction intervals.
result Proposed approach constructs honest confidence intervals with shorter lengths and better calibration.
This paper proposes a fast method for estimating input-dependent prediction intervals in Extreme Learning Machines.
problem Estimating reliable prediction intervals for Extreme Learning Machines with heteroscedastic outputs.
method A separate Extreme Learning Machine model estimates input-dependent prediction intervals using a weighted Jackknife method to correct for model uncertainty.
result The proposed method is fast, robust to heteroscedastic outputs, and handles large datasets and insufficient training data.
Study on statistical inference for nonlinear stochastic approximation with Markovian data.
problem Statistical inference for nonlinear stochastic approximation algorithms with Markovian data.
method Established a functional central limit theorem for the partial-sum process of the target parameter estimate, providing asymptotic pivotal statistics for constructing confidence intervals.
result Valid and efficient asymptotic inference method for nonlinear stochastic approximation algorithms with Markovian data.
This paper addresses sampling from bounded distributions using SGLD.
problem Sampling from models with bounded variables using SGLD.
method Introduces and evaluates various mapping techniques to transform unbounded samples into bounded ones.
result Invertible Lipschitz mappings overcame the pitfalls of existing methods and achieved weak convergence.
New method calibrates deep models' uncertainty predictions.
problem Quantifying deep models' uncertainties for trustworthiness.
method Separate prediction and interval estimation with uncertainty matching.
result Significant improvements in model fidelity and calibration error.
Algorithm StoROO optimizes risk quantiles and CVaR in stochastic functions.
problem Risk-averse decision making in fields like agriculture, medicine, biology, and finance.
method StoROO is a risk optimization algorithm for stochastic black-box functions, using confidence intervals based on random-size samples.
result StoROO provides tight bounds for quantiles and CVaR, demonstrating a significant impact on optimization.
HiGrad provides statistical inference for SGD without extra cost.
problem Statistical inference for online learning with SGD.
method Hierarchical SGD with covariance structure decorrelation.
result HiGrad confidence intervals achieve asymptotically exact coverage.
A method for efficient statistical inference from online algorithms.
problem Computational constraints in online algorithms make traditional variance estimation difficult.
method HulC method that wraps around online algorithms to produce valid confidence regions.
result The HulC method produces asymptotically valid confidence regions for online algorithms.
A new Mapper algorithm optimizes data visualization through automatic parameter tuning.
problem Manual parameter tuning and fixed intervals limit the performance of the standard Mapper algorithm.
method Introduces a soft Mapper framework based on Gaussian mixture models for automatic interval construction and optimization via stochastic gradient descent.
result Demonstrates effectiveness in capturing underlying topological structures and identifying distinct subgroups.
Improved learning of relational models from partial network data.
problem Inaccurate parameter estimates for relational models from network samples.
method Stochastic gradient descent for relational logistic regression from partial network crawls.
result Accurate parameter estimates and confidence intervals achieved.
Framework improves PV forecasting by accounting for missing data uncertainty.
problem Uncertainty from missing data in PV power data.
method Combines stochastic multiple imputation with Rubin's rule.
result Improves prediction interval calibration without sacrificing point prediction accuracy.
New method improves confidence intervals for adaptive experiment results.
problem Adaptive experiments complicate statistical inference, especially when estimating sub-optimal treatments.
method Adaptive reweighting of inverse propensity weighting terms to control variance and ensure correct coverage.
result The method prevents heavy-tailed estimates and increases hypothesis testing power.
SCOTCH learns system structure from irregular time series using neural SDEs.
problem Learning system structure from irregular time series data.
method SCOTCH uses neural stochastic differential equations (SDE) with variational inference.
result SCOTCH improves structure learning performance on synthetic and real-world datasets.
Paper proposes an online estimator for covariance matrix of SGD iterates.
problem Quantifying variability and randomness of SGD-based estimates in online learning.
method Proposes a fully online estimator for covariance matrix of ASGD using SGD iterates.
result Establishes consistency of the online estimator and shows comparable convergence rate to offline methods.
A new UCB policy improves reward-cost ratio estimation in budgeted MAB.
problem Maximizing reward-cost ratio under budget constraints.
method ω-UCB policy with asymmetric confidence intervals.
result Logarithmic regret and superior performance in various settings.
We present a theory of homogeneous volatility bridge estimators for log-price stochastic processes. The main tool of our theory is the parsimonious encoding of the information contained in the open, high and low prices of incomplete bridge, corresponding to given log-price stochastic process, and in its close value, fo…
Bayesian method estimates volatility from discrete data.
problem Estimating volatility from discrete time observations.
method Nonparametric Bayesian approach with IGMC prior on piecewise constant volatility.
result Good results in simulation and real-world applications.
Proposes a deep learning framework for interval-censored survival data.
problem Lack of deep learning methods for interval-censored survival data.
method Partially linear transformation models with DNN approximations for nonlinear effects.
result DNN estimator achieves minimax-optimal convergence and superior performance.
This research improves deep neural networks for parameter identification and prediction in stochastic Volterra integral equations.
problem Parameter identification and prediction in Volterra integral equations driven by Gaussian noise.
method Improved deep neural networks framework that incorporates inter-output relationships into the loss function.
result The framework enhances parameter estimation accuracy and provides accurate solutions for modeling stochastic systems.
Proposes BSI for valid statistical inference on bandit algorithms.
problem Valid statistical inference on bandit algorithms' performance.
method Fits a simulator of the bandit environment from observed data and uses it to estimate mean reward under any policy.
result Proves asymptotically valid confidence intervals and maintains nominal coverage.
Study on stock returns tail probabilities using stochastic volatility models.
problem Understanding tail probabilities of stock returns in stochastic volatility models.
method Analyzes stochastic differential equations for volatility, applies dimensional analysis, and uses Kolmogorov forward equation.
result Tail probabilities for short-term returns fall off like an inverse cubic and scale with the measurement interval to the power 3/2.
New CTRW model explains volatility clustering in stock markets.
problem Missing models for long-term memory in time intervals between observations.
method Introduced a new family of CTRWs with correlated waiting times.
result Successfully describes the decay of nonlinear autocorrelation function in stock market returns.