CATS adapts multivariate time series models by addressing correlation shift.
problem Correlation differences across domains in multivariate time series data.
method CATS introduces correlation shift to measure domain differences, and uses a graph attention module and temporal convolution to align target correlations with source correlations.
result CATS increases over 10% average accuracy compared to vanilla Transformer-based models with minimal additional parameters.
New method disentangles latent subspaces under correlation shifts.
problem Correlations between factors of variation make disentanglement models less robust.
method Enforces independence between subspaces conditioned on available attributes using adversarial CMI minimization.
result Models are disentangled and robust under correlation shifts, including in weakly supervised settings.
The Multi Variate Mixture Dynamics model is a tractable, dynamical, arbitrage-free multivariate model characterized by transparency on the dependence structure, since closed form formulae for terminal correlations, average correlations and copula function are available. It also allows for complete decorrelation between…
Develops correlation number for specific potentials and Hitchin representations.
problem Analyzing correlation numbers for potentials with entropy gaps and Hitchin representations.
method Defines a correlation number for pairs of cusped Hitchin representations and explores its connection to the Manhattan curve.
result Establishes a connection between the correlation number and the Manhattan curve, revealing rigidity properties.
The paper analyzes Nordic stock markets' correlation structures and regime shifts.
problem Understanding and exploiting regime shifts in Nordic stock markets.
method Examined two decades of daily data for OMXS30, OMXC20, and OMXH25 universes; proposed an adaptive portfolio allocation framework.
result Documented pronounced regime dependence in rolling correlation matrices; proposed an adaptive portfolio allocation framework.
New method disentangles correlated factors without independence assumption.
problem Learning disentangled representations from correlated data.
method Hausdorff Factorized Support (HFS) criterion for disentanglement.
result HFS consistently improves disentanglement and recovery across various correlation settings.
Improves model fairness under changing bias between labels and sensitive groups.
problem Fairness of models deteriorates when bias between labels and sensitive groups changes.
method Introduces correlation shifts to explicitly capture bias changes and proposes a pre-processing step to adjust data ratios.
result Our approach effectively improves model accuracy and fairness, both synthetic and real datasets.
SGDm with fixed step-size diverges under covariate shift, similar to a parametric oscillator.
problem SGDm with fixed step-size diverges under covariate shift.
method Approximated learning system as a time-varying system of ODEs and characterized divergence/convergence modes.
result SGDm with fixed step-size can diverge under covariate shift, similar to resonance in oscillators.
Unified framework for fairness, robustness, and distribution shifts.
problem Diverse failure modes of machine learning systems.
method Formalizes biases as violations of conditional independence and proves equivalence conditions.
result Equivalent effects of biases in different failure modes under specific conditions.
Stable Adversarial Learning improves robustness to distributional shifts.
problem Vulnerability of machine learning algorithms to distributional shifts.
method SAL algorithm that constructs a practical uncertainty set and conducts differentiated robustness optimization based on covariate stability.
result The proposed method uniformly improves performance across unknown distributional shifts.
We study the time dependent cross correlations of stock returns, i.e. we measure the correlation as the function of the time shift between pairs of stock return time series using tick-by-tick data. We find a weak but significant effect showing that in many cases the maximum correlation is at nonzero time shift indicati…
The paper shows strong correlation between in-distribution and out-of-distribution performance in various machine learning models.
problem Understanding reliability of machine learning systems in unseen environments.
method Empirical analysis of various models and distribution shifts on CIFAR-10, ImageNet, and other datasets.
result Out-of-distribution performance is strongly correlated with in-distribution performance across different models and distribution shifts.
Neural networks memorize exceptions, leading to poor generalization.
problem Memorization of exceptions hinders neural network generalization.
method Formalized memorization-generalization interplay, proposed MAT to shift logits.
result MAT improves generalization by learning robust patterns invariant across distributions.
The classical shift retrieval problem considers two signals in vector form that are related by a shift. The problem is of great importance in many applications and is typically solved by maximizing the cross-correlation between the two signals. Inspired by compressive sensing, in this paper, we seek to estimate the shi…
Method learns diverse models to resist spurious correlations.
problem Models learn spurious correlations in i.i.d. training data.
method Multiple models with minimized conditional total correlation.
result Framework significantly outperforms baseline on distribution shift.
Improves overparameterized models' robustness to distribution shifts.
problem Accuracy drop on testing distributions different from training.
method Importance tempering to improve decision boundaries.
result State-of-the-art results on worst group classification tasks.
Geostatistical learning faces unique challenges due to spatial correlation and covariate shifts.
problem Challenges in applying statistical learning to geospatial data.
method Assessing generalization error under covariate shift and spatial correlation.
result No classical learning methods are adequate for model selection in geospatial contexts.
Current OOD benchmarks overestimate model robustness to spurious correlations.
problem Spurious correlations degrade OOD performance, but benchmarks show the opposite.
method Analyze OOD datasets for spurious correlations and derive conditions for robustness.
result Current OOD benchmarks are misspecified and overestimate model robustness.
Framework uses human annotations to make models robust to spurious correlations.
problem Machine learning models fail when unmeasured variables change test distributions.
method Human annotations to augment training examples, UV-DRO objective for robustness.
result Improvements of 5-10% on digit recognition task and 1.5-5% on NYPD Police Stops analysis.
Last layer retraining improves robustness to spurious correlations without high computational costs.
problem Neural networks can rely on spurious features like backgrounds for predictions.
method Simple last layer retraining on large models.
result Last layer retraining matches or outperforms state-of-the-art approaches on spurious correlation benchmarks.
Zero-shot learning (ZSL) algorithms typically work by exploiting attribute correlations to be able to make predictions in unseen classes. However, these correlations do not remain intact at test time in most practical settings and the resulting change in these correlations lead to adverse effects on zero-shot learning …
It has been shown that instead of learning actual object features, deep networks tend to exploit non-robust (spurious) discriminative features that are shared between training and test sets. Therefore, while they achieve state of the art performance on such test sets, they achieve poor generalization on out of distribu…
LIME is a popular approach for explaining a black-box prediction through an interpretable model that is trained on instances in the vicinity of the predicted instance. To generate these instances, LIME randomly selects a subset of the non-zero features of the predicted instance. After that, the perturbed instances are …
Study on cryptocurrency trading patterns using multifractal analysis.
problem Lack of systematic study on temporal structure of cryptocurrency trading.
method Multifractal detrended cross-correlation analysis of price returns, trades, and volume.
result All analyzed quantities exhibit multifractal structure, both univariate and bivariate.
Proposes FSM-IRL to learn invariant network representations considering feature and structural shifts.
problem Spatial heterogeneity and temporal dynamics lead to OOD generalization issues in geographic networks.
method Introduces FSM-IRL model that accounts for feature and structural distribution shifts using causal attention and reweighting.
result Demonstrates strong learning capabilities on geographic and social network datasets in OOD scenarios.
New method prevents classifiers from relying on spurious correlations.
problem Group invariant learning fails to prevent classifiers from depending on spurious correlations.
method Statistical independence tests to construct groups and reweight samples by group label proportion.
result New method significantly outperforms existing group invariant learning methods in generalizing to spurious correlation shifts.
Develops a new random forest method for clustered data with improved prediction and inference.
problem Improving prediction and inference accuracy for clustered data with within-cluster dependence.
method Clustered Random Forests, using weighted least squares estimators for leaf predictions.
result Optimal prediction and inference weights vary under covariate shift, necessitating user-chosen weights.
PFDL improves deep learning models' OOD generalization by decorrelating feature embeddings.
problem Out-of-distribution generalization in deep learning models.
method PFDL algorithm that optimizes feature decomposition network and image classification model.
result PFDL improves the accuracy of image classification models on OOD datasets.
We have recently introduced the ``thermal optimal path'' (TOP) method to investigate the real-time lead-lag structure between two time series. The TOP method consists in searching for a robust noise-averaged optimal path of the distance matrix along which the two time series have the greatest similarity. Here, we gener…
The article generalizes Pearson correlation to Riemannian manifolds.
problem Analyzing statistical models on non-linear manifolds.
method Reconstitutes Pearson correlation properties and derives a nonlinear generalization.
result Developed the Riemann-Pearson Correlation for manifold analysis.
CTRF combines logged data and randomized experiments for robust prediction.
problem Robust prediction models to handle distributional shifts between training and testing data.
method CTRF uses existing training data and a small amount of randomized experiment data to train a robust model.
result CTRF produces robust predictions and outperforms baseline methods in the presence of feature shifts.
We study the sample complexity of canonical correlation analysis (CCA), \ie, the number of samples needed to estimate the population canonical correlation and directions up to arbitrarily small error. With mild assumptions on the data distribution, we show that in order to achieve ε-suboptimality in a properly define…
Enhances UPSA to reduce noise in financial data.
problem Noise in financial data affects UPSA's performance.
method Time-averaging optimal penalty weights and using Average Oracle correlation eigenvalues.
result Combining time-averaging and Average Oracle correlation eigenvalues improves UPSA's performance.
TTLSA adapts models to label shifts across domains with nuisance factors.
problem Adapting models to changes in label distributions with nuisance factors.
method TTLSA uses EM on unlabeled samples to adapt a trained model to new label distributions.
result TTLSA improves model performance over invariance methods and baseline methods.
The detrending moving average (DMA) algorithm is one of the best performing methods to quantify the long-term correlations in nonstationary time series. Many long-term correlated time series in real systems contain various trends. We investigate the effects of polynomial trends on the scaling behaviors and the performa…
We analyse the temporal changes in the cross correlations of returns on the New York Stock Exchange. We show that lead-lag relationships between daily returns of stocks vanished in less than twenty years. We have found that even for high frequency data the asymmetry of time dependent cross-correlation functions has a d…
Method improves simulation accuracy by mitigating distribution shift in hybrid systems.
problem Mitigating distribution shift in machine-learning augmented hybrid simulation.
method Tangent-space regularized estimator to control distribution shift.
result Marked improvements in simulation accuracy, especially for systems with high distribution shift.
Unsupervised learning representations generalize better than supervised learning under distribution shifts.
problem Robustness of unsupervised representations to distribution shift.
method Extensive evaluation on synthetic and realistic datasets, including controllable domain generalization datasets.
result Unsupervised representations learned from SSL and AE generalize better than supervised learning under various distribution shifts.
New method learns models to adapt to domain shifts at test time.
problem Learning models robust to distribution shifts in practical applications.
method Adaptive Risk Minimization (ARM) framework.
result Performance gains of 1-4% on image classification problems.
New measures quantify dependence between variables without distribution estimation.
problem Measuring dependence between variables in arbitrary dimensions.
method Proposed matrix-based normalized total correlation and dual total correlation measures.
result Measures are differentiable and statistically more powerful than existing methods.
Financial data has been extensively studied for correlations using Pearson's cross-correlation coefficient ρ as the point of departure. We employ an estimator based on recurrence plots --- the Correlation of Probability of Recurrence (CPR) --- to analyze connections between nine stock indices spread worldwide. We sugge…
Measures collectivity in financial covariances and correlations to reveal trends and precursors.
problem Capturing collective motion in financial markets to predict trends and precursors.
method Measures collectivity using the largest eigenvalue and average sector collectivity.
result Identifies collective signals around major financial events and captures trends in covariances and correlations.
We derive the exact form of the eigenvalue spectra of correlation matrices derived from a set of time-shifted, finite Brownian random walks (time-series). These matrices can be seen as random, real, asymmetric matrices with a special structure superimposed due to the time-shift. We demonstrate that the associated eigen…
We give a detailed account of correlations between credit sector/quality and treasury curve factors, using the robust framework of the Barclays POINT Global Risk Model. Consistent with earlier studies, we find a strong negative correlation between sector spreads and rate shifts. However, we also observe that the correl…
Causal Imitation Learning handles noisy measurements and distribution shifts.
problem Learning from noisy state observations and distributional shifts.
method Causal inference framework and adversarial RKHS learning.
result Improved robustness to distribution shifts compared to standard methods.
Bitcoin's integration with major financial indices intensifies, suggesting a shift from alternative to integrated asset.
problem Understanding Bitcoin's evolving role in financial markets and its correlation dynamics.
method Rolling-window correlation, static correlation coefficients, and event-study framework on daily data from 2018 to 2025.
result Correlation levels between Bitcoin and major indices reached 0.87 in 2024, indicating a more integrated role.
TRACE analyzes risk changes in models trained on shifted data.
problem Understanding performance changes when a model trained on shifted data is used.
method TRACE framework decomposes risk change into four factors: generalization gaps, model change penalty, and covariate shift penalty.
result TRACE provides a diagnostic tool to understand and quantify risk changes due to covariate shift.
Paper addresses uncertainty in model generalization under regime shifts.
problem Uncertainty in model generalization under regime changes.
method Proposes a framework to quantify and separate regime mismatch and sensitivity.
result Obtains exact decomposition and minimax lower bound for regime-aware models.