Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,742 papers · 148 categories

Trend · papers per month

4896143191 · May 202619922001200920172026
48 results for canonical calibration

Proposes a new calibration error estimator for deep neural networks.

problem Improves calibration of deep neural networks, especially for canonical calibration.
method Uses a Dirichlet kernel density estimate to create a low-bias, trainable calibration error estimator.
result Asymptotically converges to true LpL_p calibration error, enabling efficient estimation and mini-batch updates.

This paper rethinks confidence calibration under covariate shifts.

problem Calibration methods struggle with covariate shifts and unstable importance weighting.
method Derives Expectation consistency condition and proposes Expectation consistency loss (ECL).
result ECL loss is compatible with various types of calibration and has the same sample complexity as ECE.

Proposes h-calibration for improving miscalibrated probability outputs of neural networks.

problem Improving reliability of probability outputs from neural networks.
method Probabilistic learning framework for calibration, including a simple yet effective post-hoc algorithm.
result Significantly better performance than traditional methods, validated by experiments.

The paper explores connections between quaternionic and Cayley calibrations in dimensions 8 and 16.

problem Exploring connections between quaternionic and Cayley calibrations in dimensions 8 and 16.
method Starting from collections of 'Kähler 2-forms', the paper constructs canonical 4-forms and calibrated 4-planes in dimensions 8 and 16.
result Explicit formulas for canonical 4-forms ΦSpin(8)Φ_{Spin(8)} and ΦSpin(7)U(1)Φ_{Spin(7)U(1)} are derived, and their calibrated 4-planes are characterized.

The squashed 7-sphere S7S^{7} is a 7-sphere with an Einstein metric given by the canonical variation and its cone R8{0}\mathbb{R}^{8} - \{ 0 \} has full holonomy Spin(7){\rm Spin}(7). There is a canonical calibrating 4-form ΦΦ on R8{0}\mathbb{R}^{8} - \{ 0 \}. A minimal 3-submanifold in S7S^{7} is called associative if its cone …

2014-11-21abs ↗pdf ↗

Optimizes calibration error estimators for better classifier trustworthiness.

problem Lack of guidance on selecting and tuning calibration error estimators.
method Reformulates calibration estimation as a regression problem with i.i.d. input pairs.
result Demonstrates the effectiveness of optimized calibration estimators on image classification tasks.

This work proves L2L_2-regularized ERM controls smCE without post-hoc correction.

problem Calibration of predicted probabilities in machine learning models.
method Canonical L2L_2-regularized empirical risk minimization.
result Theoretical proof that smCE is controlled by ERM without post-hoc correction.

Study calibrated geometry in hyperkähler cones and their related spaces.

problem Characterize submanifolds in hyperkähler cones and related spaces.
method Systematic study of calibrated geometry in hyperkähler cones, 3-Sasakian manifolds, and twistor spaces.
result Obtain new characterizations of complex Lagrangian and complex isotropic cones in hyperkähler cones.

We show the total space of the canonical line bundle L\mathbb{L} of a Kahler-Einstein manifold XnX^n supports integrable SU(n+1)SU(n+1) structures, or Calabi-Yau structures. The canonical real line bundle LLL \subset \mathbb{L} over a minimal Lagrangian submanifold MXM \subset X is calibrated in this setting and hence can …

2001-09-26abs ↗pdf ↗

In this paper we study the continuum time dynamics of a stock in a market where agents behavior is modeled by a Minority Game and a Grand Canonical Minority Game. The dynamics derived is a generalized geometric Brownian motion; from the Black & Scholes formula the calibration of both the Minority Game and the Grand Can…

2012-05-11abs ↗pdf ↗

The paper constructs a lamination related to minimal hypersurfaces calibrated by a cohomology class.

problem Understanding the geometry of stable norm balls constrained by manifold topology.
method Constructing a lamination λρλ_ρ of minimal hypersurfaces calibrated by ρρ.
result Establishes a close analogy between stable norm and earthquake norms.

The paper studies affine models driven by independent Lévy processes and their calibration.

problem Characterizing and classifying affine models driven by Lévy processes.
method Analyzing the short rate equation with independent Lévy processes and characterizing the generator.
result A precise form of the generator and classification of affine models with canonical representations.

The paper studies pp-harmonic functions and their conjugates, showing they converge to calibrations of laminations.

problem Behavior of qq-harmonic functions and their conjugates in the limit as qo1q o 1.
method Analysis of pp-harmonic conjugates and their convergence to calibrations of laminations.
result The laminations calibrated by the limiting pp-harmonic conjugates are exactly those arising from the 11-Laplacian.

Let H be the hyperbolic space of dimension n+1. A geodesic foliation of H is given by a smooth unit vector field on H all of whose integral curves are geodesics. Each geodesic foliation of H determines an n-dimensional submanifold M of the 2n-dimensional manifold L of all the oriented geodesics of H (up to orientation …

2014-11-25abs ↗pdf ↗

Calibrated models can lead to miscalibrated aggregations in strategic interactions.

problem Miscalibration in aggregated predictions from multiple calibrated models.
method Analysis of strategic interactions between calibrated predictors, proving conditions for miscalibration and comparing VCG and Brier-score aggregation methods.
result VCG aggregation method outperforms Brier-score in strategic settings, providing robustness and comparable accuracy.

We present a construction of a canonical G_2 structure on the unit sphere tangent bundle S_M of any given orientable Riemannian 4-manifold M. Such structure is never geometric or 1-flat, but seems full of other possibilities. We start by the study of the most basic properties of our construction. The structure is co-ca…

2006-08-11abs ↗pdf ↗

D-GCCA improves multi-view data analysis by separating common and distinctive components.

problem Analyzing multi-view high-dimensional data with latent factors.
method Decomposes each view's data matrix into common and distinctive sources with orthogonality constraints.
result Consistent estimators with good performance and efficient computation.

In this paper we will investigate torus actions on complete manifolds with calibrations. For Calabi-Yau manifolds M^2n with a Hamiltonian structure-preserving k-torus action we show that any symplectic reduction has a natural holomorphic volume form. Moreover Special Lagrangian (SLag) submanifolds of the reduction lift…

2000-02-14abs ↗pdf ↗

A hypercomplex manifold is a manifold equipped with a triple of complex structures satisfying the quaternionic relations. A holomorphic Lagrangian variety on a hypercomplex manifold with trivial canonical bundle is a holomorphic subvariety which is calibrated by a form associated with the holomorphic volume form; this …

2013-01-02abs ↗pdf ↗

Plots show miscalibration directly as slopes of secant lines.

problem Detecting discrepancies between probabilistic predictions and actual outcomes.
method Cumulative differences between observed and expected values displayed as slopes of secant lines.
result Directly shows miscalibration without binning or kernel density estimation.

New truthful calibration errors improve model ranking in multiclass prediction.

problem Non-truthful calibration errors can mislead model comparisons.
method Introduced perfectly truthful calibration errors for multiclass predictions.
result Truthful calibration errors preserve decision-theoretic dominance and stabilize model rankings.

We propose a new framework to improve the calibration of neural networks.

problem Improving the accuracy of model confidence predictions.
method Introducing a differentiable surrogate for expected calibration error (DECE) and a meta-learning framework to optimise model hyper-parameters for validation set calibration.
result Achieved competitive performance with existing calibration approaches.

Certified calibration methods protect model confidence from adversarial attacks.

problem Adversarial attacks degrade model calibration, reducing confidence in predictions.
method Developed certified calibration methods to provide worst-case bounds on calibration under adversarial perturbations.
result Certified calibration methods produce analytic and approximate bounds for the Brier score and expected calibration error.

Meta-Cal improves post-hoc calibration of neural networks.

problem Improving the accuracy of uncalibrated neural network predictions.
method Meta-Cal uses a base calibrator and a ranking model with constraints to provide high-probability bounds.
result Meta-Cal significantly outperforms existing methods in post-hoc multi-class classification calibration.

Dead-Direction Signatures (DDS) provide a cheap, closed-form spectral reading of a network's singular complexity.

problem Estimating the complexity of deep networks through their loss singularities.
method DDS replaces the SGLD posterior chain with spectral linear algebra.
result DDS observables rank-track the network's singular complexity at the framework-predicted sign.

Post-processing predictors reduces calibration errors for decision-making.

problem Predictors with low calibration error for machine learning may have high error for decision-making.
method Post-processing with ε distance to calibration adds noise to make predictions differentially private.
result Post-processing achieves O(√ε) ECE and CDL, asymptotically optimal.

A new method for multiclass calibration using vector quantization.

problem Challenges in multiclass calibration, especially in high-stakes settings.
method Compositional approach via Vector Quantization (VQ) to learn region-specific calibration maps.
result Significant improvements in local calibration with competitive global calibration and predictive performance.

This post introduces model calibration and evaluation measures, highlighting issues with a common measure.

problem Ensuring model confidence accurately reflects true outcomes.
method Explains common calibration definition, ECE, and its drawbacks.
result New evaluation measures needed for comprehensive model calibration.

Unified calibration metrics improve forecast sharpness and accuracy.

problem Improving the sharpness of probabilistic forecasts while maintaining calibration.
method Kernel-based calibration metrics that unify and generalize existing methods for classification and regression.
result Enhanced calibration, sharpness, and decision-making across various tasks.

Smooth calibration improves forecast reliability even with leaked information.

problem Improving forecast reliability with leaked information.
method Combining nearby forecasts to ensure smooth calibration, which can be guaranteed by deterministic procedures.
result Smooth calibration can be guaranteed by deterministic procedures even with leaked forecasts, and it yields uncoupled finite-memory dynamics in games.

We describe a family of calibrations arising naturally on a hyperkähler manifold MM. These calibrations calibrate the holomorphic Lagrangian, holomorphic isotropic and holomorphic coisotropic subvarieties. When MM is an HKT (hyperkaehler with torsion) manifold with holonomy SL(n,H)SL(n, {\Bbb H}), we construct another fam…

2010-09-06abs ↗pdf ↗