Paper improves learning efficiency by focusing on effective dimensionality.
problem Dimensionality bottleneck in modern learning tasks.
method Developed tools to reduce dimensional costs using effective dimensionality.
result Uniform concentration bounds involving effective dimensionality, improving over existing results.
Model complexity is an important factor to consider when selecting among graphical models. When all variables are observed, the complexity of a model can be measured by its standard dimension, i.e. the number of independent parameters. When hidden variables are present, however, standard dimension might no longer be ap…
Paper proposes adaptive parameter selection for KGD algorithms.
problem Improving parameter selection for kernel-based gradient descent.
method Integrates bias-variance analysis with splitting method, introduces empirical effective dimension.
result Adaptive parameter selection strategy achieves optimal generalization error bound.
New method corrects Laplace/BIC errors in singular models, revealing effective dimension.
problem Laplace/BIC errors in singular models due to incorrect effective dimension assumption.
method RLCT (real log canonical threshold) to correct effective dimension in linear models.
result Correct evidence slope and effective dimension estimation in linear settings.
New method bounds high-dimensional regression without estimating design covariance.
problem High-dimensional linear regression with random design.
method Error-in-operator approach that incorporates design covariance into empirical risk minimization.
result Dimension-free bounds on excess prediction risk derived.
Adaptive rule improves kernel-based gradient descent performance.
problem Improving convergence speed of kernel-based gradient descent algorithms.
method Empirical effective dimension for stopping rule, learning theory analysis, integral operator approach.
result Optimal learning rates and iteration bounds for KGD with adaptive stopping rule.
Develops a fast variational approximation for high-dimensional empirical Bayes posteriors.
problem Optimal posterior computation in high-dimensional settings with prior tails effect.
method Variational approximation of empirical Bayes posterior with data-driven centers and thin-tailed conjugate priors.
result Retains optimal concentration rate properties and superior performance compared to existing methods.
We derive optimal statistical and computational complexity bounds for exp-concave stochastic minimization in terms of the effective dimension. For common eigendecay patterns of the population covariance matrix, this quantity is significantly smaller than the ambient dimension. Our results reveal interesting connections…
New method corrects missing data bias in dimension reduction.
problem Missing data complicates high-dimensional data analysis.
method Developed a bias-corrected Gram matrix for heterogeneous missingness.
result Proposed method improves dimension reduction techniques significantly.
Generalization in nonlinear least squares can be studied via algorithmic stability and effective dimension.
problem Generalization in nonlinear least squares models
method Deriving error bounds for local minimizers using algorithmic stability and effective dimension
result Bounds depend on learned geometry rather than parameter count
The paper evaluates biased methods for alpha-divergence minimization.
problem The impact of bias on solutions found for alpha-divergence minimization.
method Empirical evaluation of biased methods for alpha-divergence minimization, focusing on bias effects and dimensionality.
result Solutions are biased towards KL-divergence minimizers and require impractical computation in high dimensions to minimize alpha-divergence.
SGD generalizes well in high dimensions without regularization.
problem Generalization of overparameterized models in high dimensions.
method Stochastic Gradient Descent (SGD) for convex and locally convex loss functions.
result Generalization error is independent of the ambient dimension p under certain conditions. Analyzes empirical risk minimization in finance, showing effectiveness and generalization issues.
problem Analyzing empirical risk minimization in finance for optimal hedging and investment decisions.
method Classical statistical machine learning techniques and non-asymptotic estimates based on Rademacher complexity.
result Over-training leads to anticipative decisions, but non-asymptotic estimates show convergence for large training sets.
New method approximates high-dimensional probability densities efficiently.
problem Approximating high-dimensional probability densities accurately and efficiently.
method Hierarchical tensor-network approach using randomized SVD and linear equations.
result The method effectively approximates high-dimensional densities with linear complexity.
ECOD detects outliers without parameters, fast and simple.
problem Detecting outliers in large, high-dimensional datasets efficiently and interpretably.
method ECOD estimates empirical cumulative distribution functions per dimension, then computes tail probabilities and outlier scores.
result ECOD outperforms state-of-the-art methods in accuracy, efficiency, and scalability.
Estimates multiple means in high dimensions using convex combinations.
problem Estimating multiple multi-dimensional means from samples.
method Convex combinations of empirical means with data-dependent weights.
result Our methods asymptotically approach oracle (minimax) improvement.
Proposes a method to represent high-dimensional covariates for causal inference.
problem Inefficient and unreliable causal inference with high-dimensional covariates.
method Machine-learning-assisted covariate representation approach.
result Statistical reliability and performance guarantees for proposed methods.
RCNPs extend equivariant neural processes to higher dimensions, improving performance on tasks with inherent symmetries.
problem Inherently equivariant tasks in spatio-temporal modeling, Bayesian Optimization, and continuous control.
method Relational Conditional Neural Processes (RCNPs) that extend equivariances to higher dimensions.
result Empirically competitive performance on tasks with equivariances.
A new deep neural network tackles nonlinear functional regression with improved dimensionality reduction.
problem Nonlinear functional regression in infinite-dimensional functional data analysis.
method Functional deep neural network with adaptive kernel embedding and projection steps.
result Explicit rates of approximating nonlinear smooth functionals are derived, and the network is shown to be effective in both simulated and real datasets.
Variable selection and dimension reduction are two commonly adopted approaches for high-dimensional data analysis, but have traditionally been treated separately. Here we propose an integrated approach, called sparse gradient learning (SGL), for variable selection and dimension reduction via learning the gradients of t…
Deconfounding scores improve causal effect estimation with weak overlap.
problem Challenges in causal treatment effect estimation due to weak overlap in high-dimensional data.
method Propose deconfounding scores to preserve identification and target estimation while improving overlap.
result Prognostic scores are overlap-optimal under a broad family of generalized linear models with Gaussian features.
Paper uses non-linear dimension reduction for better economic forecasting.
problem Analyzing economic effects of shocks in large datasets.
method Non-linear dimension reduction in factor-augmented vector autoregressions.
result Non-linear dimension reduction techniques improve forecasting, especially in volatile data.
Theoretical and empirical taxonomy of imbalance in binary classification.
problem Class imbalance degrades binary classification performance.
method Proposed a principled framework based on three scales: imbalance coefficient, sample-dimension ratio, and intrinsic separability. Derived closed-form Bayes errors and analyzed degradation across models.
result The triplet (η, κ, Δ) provides a model-agnostic explanation of imbalance-induced deterioration.
Uncovering the heterogeneity of causal effects of policies and business decisions at various levels of granularity provides substantial value to decision makers. This paper develops new estimation and inference procedures for multiple treatment models in a selection-on-observables framework by modifying the Causal Fore…
Many 0/1 datasets have a very large number of variables; on the other hand, they are sparse and the dependency structure of the variables is simpler than the number of variables would suggest. Defining the effective dimensionality of such a dataset is a nontrivial problem. We consider the problem of defining a robust m…
Study local geometry of mixture models via spectral theory, revealing transitions in training dynamics.
problem Understanding the local geometry of high-dimensional mixture models.
method Spectral theory of Hessian and information matrices, focusing on i.i.d. Gaussian mixtures.
result Exact formulas for limits of spectral distribution and outlier eigenvalues, connecting training dynamics to effective dynamics.
Solves memorization in diffusion models for manifold data.
problem Memorization effect in diffusion models for manifold data.
method Inertia update at the end of empirical diffusion simulation.
result Approximates true data distribution on a C2 manifold. AdaScale-TuRBO improves high-dimensional Bayesian optimization by dynamically scaling the GP lengthscale.
problem Inappropriate lengthscale design in TuRBO's local GP model causes suboptimal performance in high dimensions.
method Proposes AdaScale-TuRBO, which scales the GP lengthscale with both problem dimension and trust region size.
result AdaScale-TuRBO robustly outperforms standard TuRBO and other methods on synthetic and real-world tasks.
Bayesian optimization techniques have been successfully applied to robotics, planning, sensor placement, recommendation, advertising, intelligent user interfaces and automatic algorithm configuration. Despite these successes, the approach is restricted to problems of moderate dimension, and several workshops on Bayesia…
This paper presents a novel decentralized high-dimensional Bayesian optimization (DEC-HBO) algorithm that, in contrast to existing HBO algorithms, can exploit the interdependent effects of various input components on the output of the unknown objective function f for boosting the BO performance and still preserve scala…
This work improves understanding of reinforcement learning state representations.
problem Lack of precise characterization of how and when state representations generalize.
method Developed a bound on the generalization error based on effective dimension.
result Bound quantifies the tension between generalization and approximation.
New method proves dimension-free convergence for ULD in KL divergence.
problem Polynomial scaling of existing convergence guarantees in high dimensions.
method Refined KL local error framework, focusing on tr(H) instead of d.
result First dimension-free KL divergence bounds for discretized ULD.
EigenBayes: A fast, adaptive Bayesian shrinkage approach for high-dimensional matrix factorization
problem Choosing the latent dimension k in factor models method Adaptive spectral shrinkage and empirical Bayes calibration
result Adapts to signal-to-noise ratio and shrinks superfluous components
The holy grail of deep learning is to come up with an automatic method to design optimal architectures for different applications. In other words, how can we effectively dimension and organize neurons along the network layers based on the computational resources, input size, and amount of training data? We outline prom…
Improves MARS for nonparametric multivariate regression with dimension reduction.
problem High number of basis functions in MARS for high-order interactions.
method Linear combinations of covariates for dimension reduction, facilitating gradient calculation and eigen-analysis for estimation.
result Asymptotic theory and numerical studies show improved performance over MARS.
New approach combines geometric and probabilistic methods to estimate manifold dimension in high-dimensional data.
problem Estimating the dimension of manifolds in high-dimensional data.
method Combines a modified box-counting algorithm (geometric) and a new probabilistic method (nearest neighbor distance analysis).
result The combined method is robust, fast, and effective in estimating manifold dimension.
Improved multi-group learning with group-realizable concepts.
problem Enhancing multi-group learning efficiency.
method Empirical risk minimization over group-realizable concepts.
result Improved sample complexity in group-realizable settings.
This paper evaluates fractal dimension and persistent homology for neural network generalization.
problem Bounding and predicting the generalization gap of neural networks.
method Empirical evaluation of fractal dimension and persistent homology as generalization measures.
result Fractal dimension and persistent homology fail to predict generalization of models trained from poor initializations.
We consider large scale empirical risk minimization (ERM) problems, where both the problem dimension and variable size is large. In these cases, most second order methods are infeasible due to the high cost in both computing the Hessian over all samples and computing its inverse in high dimensions. In this paper, we pr…
The paper develops a test for EU portfolio efficiency in high dimensions.
problem Testing the efficiency of the EU portfolio in high-dimensional settings.
method Shrinkage-based approach for portfolio weights and random matrix theory.
result Asymptotic behavior of the test statistic under high-dimensional conditions.
The performance of acquisition functions for Bayesian optimisation to locate the global optimum of continuous functions is investigated in terms of the Pareto front between exploration and exploitation. We show that Expected Improvement (EI) and the Upper Confidence Bound (UCB) always select solutions to be expensively…
It has long been assumed that high dimensional continuous control problems cannot be solved effectively by discretizing individual dimensions of the action space due to the exponentially large number of bins over which policies would have to be learned. In this paper, we draw inspiration from the recent success of sequ…
A new framework for dimension reduction using ensemble of random projections.
problem High-dimensional regression problems with limited data.
method Aggregating an ensemble of carefully chosen random projections, retaining based on empirical performance, and selecting singular vectors.
result The proposed method stabilizes error as the number of projection groups increases.
Neural networks' performance scales with data size, explained by data manifold dimensionality.
problem Understanding the scaling of neural network performance with the number of parameters.
method Explained by the intrinsic dimension of the data manifold, confirmed through teacher/student framework and various datasets.
result The scaling exponent α is approximately 4 divided by the intrinsic dimension d of the data manifold.
We address the problem of detecting changes in multivariate datastreams, and we investigate the intrinsic difficulty that change-detection methods have to face when the data dimension scales. In particular, we consider a general approach where changes are detected by comparing the distribution of the log-likelihood of …
Estimates dimension of subsets from random samples, proving consistency.
problem Estimating the dimension of a compact subset from random samples.
method Consistency proofs for Minkowski, correlation, and pointwise dimensions using empirical volume function.
result Statistical consistency of estimators for various dimension notions.
Dimensionality reduction (DR) on the manifold includes effective methods which project the data from an implicit relational space onto a vectorial space. Regardless of the achievements in this area, these algorithms suffer from the lack of interpretation of the projection dimensions. Therefore, it is often difficult to…
Proposes a new method to explain complex machine learning models.
problem Lack of joint feature effects in current explanation algorithms.
method Axiomatization of the Banzhaf index for capturing feature subsets.
result The generalized Banzhaf index optimally approximates black-box models.