arXiv research

New method calibrates classifier probabilities with guaranteed coverage.

The paper studies how to extend local calibration pairs to global ones in various situations. As a result, new discoveries involving mass-minimizing properties are exhibited. In particular, we show that a $\mathbb R$-homologically nontrivial connected submanifold $M$ of a smooth Riemannian manifold $X$ is homologically…

Given a transportation cost $c: M \times\bar M \to\mathbf{R}$, optimal maps minimize the total cost of moving masses from $M$ to $\bar M$. We find a pseudo-metric and a calibration form on $M\times\bar M$ such that the graph of an optimal map is a calibrated maximal submanifold. We define the mass of space-like current…

The study uses statistical methods to analyze nuclear mass models.

The paper introduces a spline-based method for calibrating neural networks.

Improves calibration of regression models without requiring additional data.

The paper develops methods to predict the probability of achieving a user goal in a task, ensuring the system alerts when the probability falls below a threshold.

Minimal networks minimize length and mass in certain configurations.

A method to monitor probability predictions for calibration loss in image classification models.

We prove that tangent cones to 2-dimensional calibrated cycles are unique. Using this result we prove a rate of convergence for the mass of the blow-up of a calibrated integral 2-cycle towards the limiting density. With the same techniques, we can also prove such a rate for J-holomorphic maps between almost complex man…

The CAP slope is Bayes' theorem in cumulative coordinates, unlocking the weight of evidence, Somers' D, and Gini coefficient.

New methods reduce bias in estimating calibration error.

Study of large mass limits of G2 and Calabi-Yau monopoles on specific manifolds.

The task of calibration is to retrospectively adjust the outputs from a machine learning model to provide better probability estimates on the target variable. While calibration has been investigated thoroughly in classification, it has not yet been well-established for regression tasks. This paper considers the problem…

New method detects strong calibration in ML models, even for small poorly calibrated subgroups.

Calibrations help estimate volumes on odd spheres without gaps.

The paper proposes a method to calibrate evidential clustering using bootstrapped finite mixture models.

Plots show miscalibration directly as slopes of secant lines.

In this paper we calibrate chaotic models for interest rates to market data using a polynomial-exponential parametrization for the chaos coefficients. We identify a subclass of one-variable models that allow us to introduce complexity from higher order chaos in a controlled way while retaining considerable analytic tra…

New findings show that not all area-minimizing surfaces are calibrated, even on complex manifolds.

This paper reviews metrics to assess AI model calibration accuracy.

Histogram binning method proven with guarantees without splitting data.

We propose a correlated stochastic process of which the novel non-Gaussian probability mass function is constructed by exactly solving moment generating function. The calculation of cumulants and auto-correlation shows that the process is convergent and scale invariant in the large but finite number limit. We demonstra…

Study three types of uncertainty quantification for binary classification without distributional assumptions.

Machine-learned anomaly detection in new-physics searches needs calibration and look-elsewhere correction

The paper extends conformal risk control to be valid with high probability over a growing calibration dataset.

Calibration of stochastic local volatility (SLV) models to their underlying local volatility model is often performed by numerically solving a two-dimensional non-linear forward Kolmogorov equation. We propose a novel finite volume (FV) discretization in the numerical solution of general 1D and 2D forward Kolmogorov eq…

DNAMite creates interpretable, calibrated survival analysis models.

The Riemannian hemisphere has a lower bound for its mass.

Bayesian framework predicts aerodynamic uncertainty from sparse measurements.

Proposes a method to create shorter, more accurate prediction intervals.

The Gilbert-Steiner problem is a mass transportation problem, where the cost of the transportation depends on the network used to move the mass and it is proportional to a certain power of the "flow". In this paper, we introduce a new formulation of the problem, which turns it into the minimization of a convex function…

Paper analyzes ECE bias and provides bounds for its estimation.

Meta-learning improves Gaussian process uncertainty estimation.

Study online monotone density estimation with expert aggregation and log-optimal calibration.

Study examines Yang-Mills-Higgs energy convergence to codimension-three area functional.

The Gaussian mechanism is an essential building block used in multitude of differentially private data analysis algorithms. In this paper we revisit the Gaussian mechanism and show that the original analysis has several important limitations. Our analysis reveals that the variance formula for the original mechanism is …

Sources of variability in experimentally derived data include measurement error in addition to the physical phenomena of interest. This measurement error is a combination of systematic components, originating from the measuring instrument, and random measurement errors. Several novel biological technologies, such as ma…

This work tackles multivariate CDFs and copulas using tensor factorization.

One of the consequences of passing from mass production to mass customization paradigm in the nowadays industrialized world is the need to increase flexibility and responsiveness of manufacturing companies. The high-mix / low-volume production forces constant accommodations of unknown product variants, which ultimately…

The paper proposes a method to construct well-calibrated prediction sets for correlated target variables.

We describe a high performance parallel implementation of a derivative pricing model, within which we introduce a new parallel method for the calibration of the industry standard SABR (stochastic-αβρ) stochastic volatility model using three strike inputs. SABR calibration involves a non-linear three dimensional minimis…

TA-CQR predicts regression intervals with exact coverage, splitting miscoverage between endpoints.

The paper prices energy spread options using a complex stochastic model.

In this work we present an analytical model, based on the path-integral formalism of Statistical Mechanics, for pricing options using first-passage time problems involving both fixed and deterministically moving absorbing barriers under possible non-gaussian distributions of the underlying object. We adapt to our probl…

Whether you trade futures for yourself or a hedge fund, your strategy is counted. Long and short position limits make the number of unique strategies finite. Formulas of the numbers of strategies, transactions, do nothing actions are derived. A discrete distribution of actions, corresponding probability mass, cumulativ…

Supervised learning is the workhorse for regression and classification tasks, but the standard approach presumes ground truth for every measurement. In real world applications, limitations due to expense or general in-feasibility due to the specific application are common. In the context of agriculture applications, yi…

CPCR mitigates bias in PCR for overparameterized models.