A new method reduces the number of features needed for kernel approximation from cubic to logarithmic.
problem Large datasets make kernel methods computationally expensive and impractical.
method Combines random feature maps with data-dependent feature selection to achieve Nystrom-like performance with fewer features.
result Achieves small kernel matrix approximation error and better test set accuracy with fewer features than state-of-the-art methods.
New feature selection method for multi-labeled data.
problem Feature redundancy in multi-labeled data.
method Conditional information measure based on dependency maximization.
result Efficient and fast non-parametric feature selection.
KernelNet learns data-dependent kernels for deep generative models.
problem Learning kernels requires careful selection of hyperparameters.
method KernelNet constructs a data-dependent kernel using deep neural networks.
result KernelNet achieves better performance in deep generative models.
Quantum neural networks need both data-dependent and trainable unitaries for effective geometric deformation.
problem Quantum neural networks lack the geometric flexibility of classical networks due to limitations in state reachability.
method Viewing quantum states as embedded manifolds, we analyze infinitesimal unitary actions and introduce the CLA maps and aCLS criterion.
result Geometric flexibility in quantum neural networks requires a joint dependence on data and trainable weights.
Bayesian neural networks explore rare fluctuations for better feature learning.
problem Understanding rare but dominant fluctuations in Bayesian neural networks.
method Large-deviation theory and joint optimization over predictors and internal kernels.
result Posterior rate function optimization reveals data-dependent kernel selection.
Unsupervised preprocessing can bias cross-validation estimates in regression models.
problem Bias in cross-validation estimates due to unsupervised preprocessing.
method Analysis of three preprocessing procedures: feature selection, grouping, and rescaling.
result Unsupervised preprocessing can introduce substantial bias into cross-validation estimates.
The paper develops a method to select features from multiple kernels for efficient risk minimization.
problem Identifying promising features leading to satisfactory out-of-sample performance in nonlinear kernel approximation.
method A greedy selection process using a correlation metric to choose features from multiple kernels.
result An out-of-sample error bound capturing trade-offs between approximation and spectral errors, showing poly-logarithmic scaling with data.
A new method for interpretable regression using data-dependent coverings.
problem Creating interpretable regression function estimators.
method Data-dependent coverings to generate a covering of the feature space instead of a partition.
result Ensures consistency without the need for shrinking cells, reducing the number of covering elements.
The randomized-feature approach has been successfully employed in large-scale kernel approximation and supervised learning. The distribution from which the random features are drawn impacts the number of features required to efficiently perform a learning task. Recently, it has been shown that employing data-dependent …
New decentralized KRR algorithm adapts to node-specific data.
problem Consistent node-specific data in decentralized KRR.
method Data-dependent random features for adaptive RF generation.
result Average regression accuracy improved by 25.5% across six datasets.
New bounds for online portfolio selection without smoothness assumptions.
problem Online portfolio selection with non-Lipschitz, non-smooth losses.
method Data-dependent bounds using novel smoothness characterizations and FTRL with self-concordant regularizers.
result Achieves logarithmic regrets when data is 'easy' and sublinear worst-case regrets.
ORCCA improves CCA performance with randomized features.
problem Improving CCA performance with randomized features.
method Proposes a task-specific scoring rule for selecting random features in CCA.
result ORCCA outperforms Kernel CCA in expectation.
Optimizes subgroup selection in clinical trials.
problem Identifying regions in feature space where a regression function exceeds a threshold.
method Formulates subgroup selection as constrained optimisation, determining minimax optimal rate for regret.
result Determines the minimax optimal rate for regret in sample size and Type I error probability.
Greedy algorithms are widely used for problems in machine learning such as feature selection and set function optimization. Unfortunately, for large datasets, the running time of even greedy algorithms can be quite high. This is because for each greedy step we need to refit a model or calculate a function using the pre…
Gaussian processes (GPs) provide a nonparametric representation of functions. However, classical GP inference suffers from high computational cost and it is difficult to design nonstationary GP priors in practice. In this paper, we propose a sparse Gaussian process model, EigenGP, based on the Karhunen-Loeve (KL) expan…
The study improves representation learning bounds using data-dependent Gaussian mixtures.
problem Improving generalization in representation learning.
method Established bounds using relative entropy and MDL of latent variables.
result The approach significantly improves generalization over existing methods.
Deep and wide ReLU networks learn data-dependent features even in the lazy training regime.
problem Understanding the behavior of neural networks with finite depth and width.
method Analyzing the mean and variance of the neural tangent kernel (NTK) in a randomly initialized ReLU network.
result The NTK has a non-trivial evolution during training, with the mean of its first SGD update being exponential in the ratio of depth to width.
Paper extends distributed learning with random features to non-attainable cases.
problem Generalization properties for distributed learning with random features under non-attainable conditions.
method Refined proof techniques, data-dependent generating strategy, additional unlabeled data.
result Remarkably reduces computational cost while preserving optimal generalization accuracy.
This paper improves random feature sampling using empirical leverage scores.
problem Optimizing the number of features for kernel approximation and supervised learning.
method Uses empirical leverage scores to optimize feature sampling.
result Empirical sampling of random features using leverage scores outperforms vanilla Monte Carlo sampling.
Improved DNN robustness to adversarial attacks using data-dependent activation and total variation minimization.
problem Improving Deep Neural Network robustness to adversarial attacks.
method Data-dependent activation function and total variation minimization.
result Robust accuracy of adversarially trained ResNet20 increased from ~46% to ~69% under IFGSM attack.
A framework for uncertainty-aware multimodal learning using conformal Shapley intervals.
problem Uncertainty and modality level importance in multimodal learning.
method Introduces conformal Shapley intervals to quantify modality level importance and uncertainty.
result Demonstrates meaningful uncertainty quantification and strong predictive performance.
Study proposes a statistical testing framework for evaluating clustering pipelines.
problem Quantifying the statistical reliability of clustering results from data analysis pipelines.
method Selective inference-based statistical testing framework for clustering pipelines.
result The proposed test controls the type I error rate and is effective in validating clustering results.
A new MMD-based test combines kernels for two-sample testing without splitting data.
problem Efficiently testing if two datasets come from the same distribution without splitting data.
method Proposes a novel statistic based on Maximum Mean Discrepancy (MMD) that combines kernels, proving concentration bounds and showing data-dependent kernel selection.
result Exponential concentration bounds and improved test power compared to existing methods.
PS-DME evaluates model performance and reliability after data-dependent selection.
problem Evaluating model performance and reliability when data is used for selection and evaluation.
method Post-selection distributional model evaluation (PS-DME) using e-values to control false coverage rate.
result PS-DME provides reliable comparison of model configurations across different reliability levels.
Kernel methods are powerful and flexible approach to solve many problems in machine learning. Due to the pairwise evaluations in kernel methods, the complexity of kernel computation grows as the data size increases; thus the applicability of kernel methods is limited for large scale datasets. Random Fourier Features (R…
A new method generates mixed-type features in tabular data with improved realism and accuracy.
problem Generating mixed-type features combining discrete and continuous data is challenging.
method A cascaded approach: first generates low-resolution categorical and coarse numerical features, then uses these in a high-resolution flow matching model.
result The model significantly improves detection scores, generating more realistic samples and capturing distributional details.
Adaptive source selection for positive transfer in linear models improves target dataset performance.
problem Limited task-specific labeled data in business settings.
method Greedily decides from which sources and how many samples to incorporate into the target dataset using an accept/reject rule based on a data-dependent estimate of the transfer gain.
result Consistent gains over classical and recent strong baselines while avoiding negative transfer.
Develops methods to adjust prediction set coverage based on post-selection analysis.
problem Adjusting prediction set coverage after initial analysis to better fit specific needs.
method Post-selection conformal inference to adjust miscoverage levels.
result Allows for trade-off between coverage and prediction set quality.
Paper establishes a generalization bound for gradient flow using a data-dependent kernel.
problem Understanding the generalization properties of gradient-based optimization methods.
method Establishes a generalization bound for gradient flow through a data-dependent kernel called the loss path kernel (LPK).
result The LPK captures the entire training trajectory and leads to tighter generalization guarantees.
Neural networks require a careful design in order to perform properly on a given task. In particular, selecting a good activation function (possibly in a data-dependent fashion) is a crucial step, which remains an open problem in the research community. Despite a large amount of investigations, most current implementat…
Proposes DP-MERF for privacy-preserving synthetic data generation.
problem Privacy-preserving data generation for synthetic datasets.
method Differentially private mean embeddings with random features.
result Achieves better privacy-utility trade-offs than existing methods.
Algorithm provides online learning guarantees against general comparators in full and bandit feedback.
problem Adversarial online learning with data-dependent regret guarantees.
method Completely online algorithm with data-dependent regret guarantees for full and bandit feedback.
result Algorithm achieves expected performance against arbitrary comparator sequences in full and bandit feedback settings.
Proposes tensor Q-rank for better tensor rank recovery in complex data.
problem Improving tensor rank recovery for complex data with low sampling rate.
method Introduces tensor Q-rank and two selection methods for Q, proposing VMTQN and MOTQN models. result Demonstrates superior performance in tensor completion problems compared to TNN-based methods.
The paper studies multi-view representation learning with generalization guarantees and a new regularizer.
problem Distributed multi-view representation learning with correct estimation at a decoder.
method Generalization bounds using relative entropy and MDL, data-dependent Gaussian mixture priors.
result Data-dependent Gaussian mixture priors lead to good performance and outperform existing methods.
aLTT selects hyperparameters efficiently with statistical guarantees.
problem Statistical validity and efficiency in hyperparameter selection.
method Sequential data-dependent multiple hypothesis testing with early termination.
result Reduces testing rounds while maintaining statistical validity.
Study on generalization for data-dependent hypothesis sets.
problem Understanding generalization in hypothesis sets dependent on data.
method Learning guarantee based on transductive Rademacher complexity and hypothesis set stability.
result Generalization bound for data-dependent hypothesis sets.
We present a new technique called contrastive principal component analysis (cPCA) that is designed to discover low-dimensional structure that is unique to a dataset, or enriched in one dataset relative to other data. The technique is a generalization of standard PCA, for the setting where multiple datasets are availabl…
A new deep learning approach enhances signature transforms for data analysis.
problem Improving data analysis through more flexible signature transforms.
method Combining deep learning with signature transforms to select terms data-dependently.
result Signature transform can be used as a pooling operation within neural networks.
The study characterizes diffusion model generalization using data-dependent ridge manifolds.
problem Understanding where diffusion model-generated samples lie when not memorizing the training set.
method Introduced a time-dependent family of log-density ridge manifolds to characterize reverse-time inference.
result Generated samples evolve by a reach-align-slide mechanism, controlled by normal and tangential components of training error.
We reformulate data-dependent constraints to ensure they are always met with high probability.
problem Ensuring fairness and stability in machine learning models with data-dependent constraints.
method Calibrated reformulation of constraints to guarantee satisfaction with a specified probability.
result Our method guarantees that fairness constraints are met at test time with high probability.
Paper proposes a new method to learn distribution kernels via entropy maximization.
problem Challenges in applying kernel methods to distribution regression tasks.
method Proposes a novel objective for unsupervised learning of data-dependent distribution kernels based on entropy maximization.
result Demonstrates the effectiveness of the learned kernel across different modalities.
A new neural network model reduces features in high-dimensional sequential data.
problem Exponential growth in features of truncated signature transform in high-dimensional data.
method Proposes a neural network model inspired by Convolutional Neural Networks to address feature growth.
result Reduces the number of features efficiently in a data-dependent way.
Model selection based on classical information criteria, such as BIC, is generally computationally demanding, but its properties are well studied. On the other hand, model selection based on parameter shrinkage by ℓ1-type penalties is computationally efficient. In this paper we make an attempt to combine their st…
We propose a general framework for studying adaptive regret bounds in the online learning framework, including model selection bounds and data-dependent bounds. Given a data- or model-dependent bound we ask, "Does there exist some algorithm achieving this bound?" We show that modifications to recently introduced sequen…
Conformal Alignment ensures trustworthy outputs from foundation models.
problem Ensuring outputs from foundation models align with human values in high-stakes tasks.
method A framework that trains an alignment predictor using reference data to select trustworthy outputs.
result Conformal Alignment accurately identifies trustworthy outputs via lightweight training over moderate reference data.
Study how generalization scales with model size and data in quadratic neural networks.
problem Understanding how generalization scales with model size and data in quadratic neural networks.
method Analyzed ℓ2-regularized empirical test error minimization in a quadratic two-layer network with finite-sample setting and structured data. result Revealed a phase diagram with distinct scaling regimes as the number of parameters varies, showing data-dependent power laws controlled by spectral structure of the target.
PAC-Bayesian theory applied to data-dependent hypothesis sets yields uniform generalization bounds.
problem Proving uniform generalization bounds for data-dependent hypothesis sets.
method Applying PAC-Bayesian framework on 'random sets' and considering data-dependent hypothesis sets.
result Data-dependent uniform generalization bounds are proven, providing tighter and unified results.
Feature bagging improves stability through random feature subsampling.
problem Improving the stability of ensemble learning methods.
method Introducing feature instability (FI) and analyzing feature bagging in parametric and model-free settings.
result Feature bagging provides stronger stability than non-bagged methods, especially with aggressive subsampling.