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.

168,695 papers · 148 categories

Trend · papers per month

226451677902 · Jun 202019922001200920172026
48 results for Fit Improvement

We propose a data aggregation-based algorithm with monotonic convergence to a global optimum for a generalized version of the L1-norm error fitting model with an assumption of the fitting function. The proposed algorithm generalizes the recent algorithm in the literature, aggregate and iterative disaggregate (AID), whi…

2017-03-15abs ↗pdf ↗

Improved modeling of persistence diagrams for data analysis.

problem Determining significant outliers in persistence diagrams.
method Modification of the RST (Replicating Statistical Topology) model using MCMC Metropolis-Hastings algorithm.
result The modified RST model improves the goodness of fit in persistence diagram analysis.

Improved KSD test for better detection of differences in distributions.

problem Low power of KSD test when distributions have same modes but different mixing proportions.
method Perturb the observed sample using Markov transition kernels to improve KSD test power.
result Perturbed KSD test can lead to substantially higher power than the original KSD test.

This paper improves volatility forecasting using dynamic subset selection in genetic programming.

problem Improving accuracy of implied volatility forecasting.
method Dynamic training-subset selection methods applied to genetic programming.
result Dynamic subset selection improves predictive accuracy of genetic programming models.

A new method improves fitting neural data with spiking network models.

problem Fitting spiking network models to neural activity does not produce realistic data.
method Augment log-likelihood with dissimilarity terms measured by summary statistics and optimized via back-propagation.
result The new method generates more realistic neural activity statistics and improves network connectivity inference.

Improved SSD for faster and more accurate goodness-of-fit tests and model learning.

problem Optimal slicing directions for SSD are computationally expensive and sub-optimal.
method Relaxed optimal slicing requirement, active sub-space construction, spectral decomposition.
result 14-80x speed-up in goodness-of-fit tests compared to gradient-based alternatives.

We present and evaluate the Fast (conditional) Independence Test (FIT) -- a nonparametric conditional independence test. The test is based on the idea that when P(XY,Z)=P(XY)P(X \mid Y, Z) = P(X \mid Y), ZZ is not useful as a feature to predict XX, as long as YY is also a regressor. On the contrary, if $P(X \mid Y, Z) \neq P(X…

2018-04-08abs ↗pdf ↗

Improved nuclear cross section fitting with weighted Levenberg-Marquardt method.

problem Challenging optimization in multichannel nuclear cross section data.
method Weighted Levenberg-Marquardt algorithm with Fisher Information Metric.
result More physically consistent fits for raw and smoothed datasets.

New method improves feasibility of fitting Gaussian vectors to an ellipsoid.

problem Feasibility of fitting nn Gaussian vectors to an ellipsoid boundary.
method Improved concentration of Gram matrices using Bartl & Mendelson (2022) results.
result Feasibility of (P)(\mathrm{P}) with high probability when nd2/Cn \leq d^2 / C.

In regression modelling approach, the main step is to fit the regression line as close as possible to the target variable. In this process most algorithms try to fit all of the data in a single line and hence fitting all parts of target variable in one go. It was observed that the error between predicted and target var…

2018-05-04abs ↗pdf ↗

The problem of automatic software generation is known as Machine Programming. In this work, we propose a framework based on genetic algorithms to solve this problem. Although genetic algorithms have been used successfully for many problems, one criticism is that hand-crafting its fitness function, the test that aims to…

2019-08-22abs ↗pdf ↗

Sliced kernelized Stein discrepancy improves goodness-of-fit tests and model learning in high dimensions.

problem The curse-of-dimensionality in kernelized Stein discrepancy (KSD).
method Sliced Stein discrepancy and its scalable variants using optimal one-dimensional projections.
result Significantly outperforms KSD and baselines in goodness-of-fit tests and improves model learning.

Improves model accuracy for neural nets in stochastic dynamics with partial prior knowledge.

problem Stability and accuracy in neural nets modeling stochastic dynamics with many parameters.
method Three steps: probabilistic weights, partial knowledge incorporation, and PAC-Bayesian training.
result Improved model fit with partial and noisy prior knowledge.

New deep learning methods improve estimation and GOF assessment for large-scale IFA.

problem Estimating and assessing goodness-of-fit for large-scale confirmatory IFA models.
method Extended deep learning algorithm for parameter estimation and simulation-based tests for GOF assessment.
result Proposed methods provide comparable estimates and detect latent dimensionality misspecification.

The paper solves the problem of fitting an ellipsoid to random points efficiently.

problem Finding an ellipsoid that passes through random Gaussian points.
method Constructing a fitting ellipsoid using a decomposition of a random matrix and graph matrix theory.
result The ellipsoid fitting problem transitions from feasible to infeasible at a sharp threshold of nd2/4n \sim d^2/4.

Fourier representation improves KSD for infinite-dimensional data.

problem Applying KSD to infinite-dimensional data.
method Combining measure equations with kernel methods for a Fourier representation of KSD.
result KSD can separate measures in infinite-dimensional Hilbert spaces.

New ABC method improves Bézier simplex fitting for noisy data.

problem Overfitting in Bézier simplex fitting when sample points are not on the Pareto set.
method Extended Bézier simplex model to a probabilistic one and proposed a new learning algorithm based on approximate Bayesian computation (ABC) with Wasserstein distance.
result The new algorithm converges on a finite sample and outperforms deterministic methods on noisy instances.

Improved estimators for causal inference using cross-fitting and undersmoothing.

problem Estimating expected conditional covariance in causal inference.
method Double cross-fit doubly robust (DCDR) estimators with undersmoothing for non-smooth nuisance functions.
result DCDR estimators achieve n\sqrt{n}-consistency and asymptotic normality under minimal conditions.

Improving scalability and stability of Stein discrepancies for scalable goodness-of-fit testing

problem Improving scalability and stability of Stein discrepancies for scalable goodness-of-fit testing
method Reformulating Stein discrepancy construction as an explicit SNR^2 maximisation problem
result Avoiding exponential SNR^2 collapse and achieving stable SNR^2

Combines datasets to improve model fitting with small sample sizes.

problem Improving model performance with limited samples from at least one dataset.
method Proposes a novel framework called Combine datasets based on Imputation (ComImp) and PCA-ComImp for combining datasets with missing data.
result Significant improvement in model accuracy, especially with small datasets and when combined with transfer learning.

Improves decision-making in models fit with AEVB by using distinct approximate posteriors.

problem Bias in expected risk estimates due to variational distribution use.
method Use multiple approximate posteriors, including those distinct from variational, for decision-making.
result Proposed approach outperforms state-of-the-art methods in single-cell RNA sequencing.

RAMs improve GAMs' accuracy by fitting components to subregions of feature space.

problem Subpar accuracy in GAMs due to inability to capture feature interactions.
method Identify subregions of feature space where interactions are minimized, fitting one component per subregion.
result RAMs offer improved expressiveness compared to GAMs while maintaining interpretability.