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.

168,657 papers · 148 categories

Trend · papers per month

3216439641,285 · Jun 202019922001200920172026
48 results for synthetic data benchmark

Generates synthetic data for benchmarking unsupervised outlier detection.

problem Difficulty in benchmarking unsupervised outlier detection due to rare and varied outliers in real data.
method Proposes a generic process to generate synthetic data with insightful characteristics.
result Demonstrates practicality of the generic process through a benchmark with state-of-the-art detection methods.

A Python tool generates synthetic data for cluster analysis from high-level descriptions.

problem Creating synthetic data for cluster analysis is laborious and requires detailed geometric parameters.
method Proposes natural language-based synthetic data generation and implements it in a Python package.
result Makes it easy to set up interpretable and reproducible benchmarks for cluster analysis.

SurvHTE-Bench benchmarks HTE estimation in survival analysis with diverse datasets.

problem Challenges in estimating HTEs from right-censored survival data.
method Modular synthetic datasets, semi-synthetic datasets, and real-world datasets.
result First rigorous comparison of survival HTE methods under diverse conditions.

Scoping review and benchmarking of synthetic EHR data generation methods.

problem Creating realistic synthetic electronic health records for research and training.
method Conducted a scoping review and benchmarked seven methods on open-source EHR datasets.
result GAN-based methods excel in fidelity and utility, while rule-based methods excel in privacy protection.

RealCause provides a realistic benchmark for causal inference.

problem Lack of a reliable benchmark for comparing causal effect estimators.
method Flexible generative models to create a benchmark that is both ground-truth and realistic.
result Evaluation of over 1500 causal estimators provides evidence for choosing hyperparameters using predictive metrics.

DSLOB creates synthetic LOB data for benchmarking forecasting algorithms under distributional shifts.

problem Challenges in dealing with out-of-distribution limit order book data.
method Multi-agent market simulator to create labeled synthetic LOB dataset with and without market stress.
result Demonstrates the need for robust forecasting algorithms to handle distributional shifts.

Paper introduces TAP-Vid, a benchmark for tracking any point in videos.

problem Tackles the problem of tracking arbitrary physical points on surfaces over longer video clips.
method Formalizes the problem as TAP, introduces TAP-Vid benchmark, uses crowdsourced pipeline with optical flow estimates, proposes TAP-Net model.
result TAP-Net outperforms all prior methods on TAP-Vid benchmark when trained on synthetic data.

The report evaluates heuristics for learning timescale graphical event models.

problem Lack of heuristics for determining hyper-parameters in timescale graphical event models.
method Proposed and evaluated different heuristics for hyper-parameter determination and refined an existing distance measure.
result Conclusions about the applicability of different heuristics on synthetic data.

TempoPFN models for zero-shot time series forecasting using synthetic data.

problem Efficient long-horizon prediction and reproducibility in zero-shot time series forecasting.
method Linear RNNs pre-trained on synthetic data with GatedDeltaProduct architecture and state-weaving.
result Achieves top-tier competitive performance on various benchmarks.

FinStressTS creates synthetic benchmarks for financial forecasting, revealing model weaknesses.

problem Limited failure attribution in real-world financial benchmarks.
method Synthetic benchmark with 30 diagnostic environments linked to six mechanism families.
result Model performance varies by mechanism type, with autoregressive models often outperforming Transformers.

TimeGraph creates synthetic datasets for robust time-series causal discovery.

problem Lack of reliable synthetic benchmark datasets for robust time-series causal discovery.
method Developed comprehensive synthetic datasets with temporal properties, including trends, seasonality, and noise.
result Demonstrated significant variations in algorithm performance under realistic temporal conditions.

CTBench benchmarks cryptocurrency time series generation for trading applications.

problem Lack of comprehensive benchmarks for cryptocurrency time series generation.
method Developed a comprehensive benchmark extsf{CTBench} with 13 metrics across 5 dimensions.
result Uncovered trade-offs between statistical fidelity and real-world profitability.

Foundation models leak sensitive data in synthetic tabular data generation, especially LLaMA 3.3 70B.

problem Privacy leakage in synthetic tabular data generation using foundation models.
method Benchmarked three foundation models (GPT-4o-mini, LLaMA 3.3 70B, TabPFN v2) against four baselines on 35 real-world tables.
result Foundation models, especially LLaMA 3.3 70B, have the highest privacy risk in synthetic tabular data generation.

In this paper, we propose a novel method for generating a synthetic dataset obeying Gaussian distribution. Compared to the commonly used benchmark datasets with unknown distribution, the synthetic dataset has an explicit distribution, i.e., Gaussian distribution. Meanwhile, it has the same characteristics as the benchm…

2019-06-01abs ↗pdf ↗

Performing controlled experiments on noisy data is essential in understanding deep learning across noise levels. Due to the lack of suitable datasets, previous research has only examined deep learning on controlled synthetic label noise, and real-world label noise has never been studied in a controlled setting. This pa…

2019-11-21abs ↗pdf ↗

DIGEN benchmark provides synthetic datasets for ML algorithm evaluation.

problem Understanding and comparing machine learning algorithms' performance.
method Synthetic datasets generated using 40 mathematical functions to evaluate machine learning algorithms.
result DIGEN resource facilitates understanding why algorithms perform poorly and provides ideas for improvement.

Generates synthetic manufacturing data for causal discovery benchmarking.

problem Lack of suitable real data for validating causal discovery algorithms.
method Distributional random forests for estimating conditional distributions.
result Semisynthetic manufacturing data adheres to a causal model.

Efficient synthetic data generation improves model performance on tabular data.

problem Improving model robustness and performance with scarce or low-quality data.
method Hardness characterization to identify high-value training points, generating synthetic data only from these points.
result Synthetic data generated from hardest points outperforms non-targeted methods on tabular datasets.

New algorithms for clustering and synthetic data generation of heterogeneous tabular datasets.

problem Clustering and generating synthetic data from heterogeneous tabular datasets with hidden cluster structure.
method Developed MMM and MMMsynth algorithms for clustering and synthetic data generation.
result MMMsynth algorithm outperforms other literature tabular-data generators and approaches real data performance.

Proposes a new method for generating synthetic data using copula flows.

problem Challenges of current synthetic data generation methods, especially with mixed real and categorical variables.
method Uses normalizing flows to learn copula density and univariate marginals based on copula theory.
result Demonstrates improved synthetic data generation and density estimation.

This paper uses deep generative models to create synthetic financial data for portfolio and risk modeling.

problem Challenges in empirical research due to privacy, accessibility, and reproducibility issues in financial data.
method Investigates the use of Time-series Generative Adversarial Networks (TimeGAN) and Variational Autoencoders (VAEs) to generate synthetic financial return series.
result Synthetic data from TimeGAN closely mimics real financial data in distributional shapes, volatility, and autocorrelation.

Proposes a new framework to evaluate causal discovery methods for time series data.

problem Lack of ground truth for causal discovery in time series data.
method Flexible framework for generating synthetic time series data.
result Demonstrates degradation in performance when assumptions are violated.

Generative synthetic data can preserve predictive accuracy but distort causal inference.

problem Distortion of average treatment effect estimates in synthetic data.
method Hybrid synthetic-data framework that generates covariates while modeling treatment and outcome mechanisms separately.
result Hybrid synthesis improves causal fidelity compared to fully generative baselines.

CausalTime generates realistic time-series for TSCD evaluation.

problem Lack of realistic synthetic datasets for TSCD performance evaluation.
method Harnessing deep neural networks and normalizing flow for dynamics, extracting causal graphs, and deriving ground truth causal graphs.
result Generated datasets accurately reflect real data and ground truth causal graphs.

This study evaluates subgroup analysis methods for time-to-event outcomes in randomized controlled trials.

problem Identifying subgroups of good responders in non-significant randomized controlled trials.
method Evaluation of several subgroup analysis algorithms for time-to-event outcomes using synthetic and semi-synthetic data.
result Provides a new synthetic and semi-synthetic data generation process and an open-source Python package for benchmarking.

Generative Adversarial Networks (GANs) have made releasing of synthetic images a viable approach to share data without releasing the original dataset. It has been shown that such synthetic data can be used for a variety of downstream tasks such as training classifiers that would otherwise require the original dataset t…

2019-12-31abs ↗pdf ↗

A framework combines unsupervised and semi-supervised AD using synthetic anomalies.

problem Improving anomaly detection in both unsupervised and semi-supervised settings.
method Proposes a new framework that uses both known and synthetic anomalies for training.
result Synthetic anomalies improve anomaly modeling in low-density regions and provide optimal convergence guarantees.

SHAP Distance assesses semantic fidelity of synthetic tabular data.

problem Semantic fidelity of synthetic tabular data is not well evaluated.
method SHAP Distance, defined as cosine distance between global SHAP attribution vectors.
result SHAP Distance detects semantic discrepancies overlooked by standard measures.

Improved Compressed Sensing by optimizing sparse solutions with mixed integer programming.

problem Finding sparse solutions to linear measurements with numerical tolerance.
method Introducing an 2\ell_2 regularized formulation, reformulating as a mixed integer second order cone program, deriving a second order cone relaxation, and developing a custom branch-and-bound algorithm.
result Our approach produces solutions that are on average 6.22% more sparse compared to state-of-the-art methods.