Transformers handle infinite dimensional inputs effectively by feature extraction and dynamic feature selection.
problem Understanding the approximation and estimation ability of Transformers with infinite dimensional inputs.
method Anisotropic smoothness analysis and feature extraction properties of Transformers.
result Transformers avoid the curse of dimensionality and dynamically select important features.
Learning sparse features can lead to overfitting in neural networks, especially for smooth target functions.
problem Understanding when feature learning in neural networks improves or deteriorates performance.
method Analyzing the effect of feature sparsity on neural network performance and comparing it to lazy training methods.
result Feature learning can lead to overfitting, especially for smooth target functions, due to sparser and less smooth representations.
The paper tackles fair representation learning by smoothing feature mappings.
problem Legal liability for discriminatory use of data by organizations.
method Mapping features to a fair representation space, certifying fairness through chi-squared mutual information.
result Smoothing representation distribution provides generalization guarantees of fairness and maintains accuracy for downstream tasks.
Graph smoothing can improve learning performance by restoring lost information.
problem Graph Neural Networks (GNNs) can oversmooth, losing important information.
method Analyzing simplified linear GNNs with mean aggregation, showing benefits up to a certain point.
result Graph smoothing can restore lost information, improving both regression and classification.
In text classification, dictionaries can be used to define human-comprehensible features. We propose an improvement to dictionary features called smoothed dictionary features. These features recognize document contexts instead of n-grams. We describe a principled methodology to solicit dictionary features from a teache…
Matrix factorisation methods decompose multivariate observations as linear combinations of latent feature vectors. The Indian Buffet Process (IBP) provides a way to model the number of latent features required for a good approximation in terms of regularised reconstruction error. Previous work has focussed on latent fe…
Off-the-shelf Gaussian Process (GP) covariance functions encode smoothness assumptions on the structure of the function to be modeled. To model complex and non-differentiable functions, these smoothness assumptions are often too restrictive. One way to alleviate this limitation is to find a different representation of …
Surrogate-based analysis of interactions via local effect smooths
problem Detecting and characterizing feature interactions in machine learning models
method Surrogate-based analysis using generalized additive models
result Empirical validation of effectiveness for pairwise interactions
AGE improves graph embedding by smoothing features and iteratively enhancing node embeddings.
problem Challenges in attributed graph embedding, especially in preserving optimal low-pass characteristics and robustness.
method AGE, a novel framework combining Laplacian smoothing and adaptive encoding, addresses these issues.
result AGE consistently outperforms state-of-the-art methods on node clustering and link prediction tasks.
Proposes PSCs for UQ in deep nets without retraining.
problem Estimating uncertainty in deep nets with a single pass.
method Identifies sensitive, smooth intermediate layer, fits probabilistic model.
result PSCs achieve UQ and OOD detection performance matching existing methods.
Over the past few decades, we have witnessed a large family of algorithms that have been designed to provide different solutions to the problem of dimensionality reduction (DR). The DR is an essential tool to excavate the important information from the high-dimensional data by mapping the data to a low-dimensional subs…
Graph convolutions can enhance high frequencies, leading to over-sharpening.
problem Graph convolutions suffer from over-smoothing and poor performance on heterophilic graphs.
method Rigorously prove that linear graph convolutions minimize a generalized Dirichlet energy, showing that weight matrices induce edge-wise attraction or repulsion.
result Graph convolutions can enhance high frequencies, leading to over-sharpening instead of over-smoothing.
Dropout improves regularization in flexible models for rare features.
problem Understanding theoretical properties of dropout in generalized linear models.
method Theoretical analysis and application to adaptive smoothing with B-splines.
result Dropout prefers rare features in mean and dispersion parameters.
SStaGCN improves GCN by stacking and aggregation for better node feature extraction.
problem Mitigating over-smoothing in GCN for heterogeneous graph data.
method SStaGCN combines stacking and aggregation to improve GCN performance.
result SStaGCN effectively mitigates over-smoothing and enhances node feature extraction.
KuramotoGNN uses Kuramoto model to prevent over-smoothing in graph neural networks.
problem Over-smoothing in graph neural networks where node features become indistinguishable.
method Integrates Kuramoto model to prevent phase synchronization and instead achieve frequency synchronization.
result KuramotoGNN reduces over-smoothing on various graph deep learning tasks.
Improved kernel ridge regression for large datasets using weighted random binning.
problem Efficiently approximating kernel matrices for large-scale datasets.
method Introduced weighted random binning features for locality sensitive hashing.
result Weighted random binning features generate Gaussian processes of any desired smoothness.
Proposes a curriculum-based scheme to smooth CNN feature embeddings.
problem Distortion artifacts in early training stages of CNNs.
method Smoothes feature embedding using Gaussian kernels to control high-frequency information.
result Significant performance improvements on various vision tasks.
The problem of joint feature selection across a group of related tasks has applications in many areas including biomedical informatics and computer vision. We consider the l2,1-norm regularized regression model for joint feature selection from multiple tasks, which can be derived in the probabilistic framework by assum…
Unified view of GNNs as graph signal denoising.
problem Understanding and improving GNNs for graph data.
method Established GNNs as graph denoising problems with smoothness assumptions.
result Unified framework UGNN for adaptive smoothness graphs.
DFIV uses deep features for IV regression, achieving optimal rates.
problem Optimal IV regression with deep features for complex target functions.
method Two-stage approach: deep feature learning followed by IV regression.
result DFIV achieves minimax optimal learning rate under certain conditions.
A hierarchical model shows how scaling laws emerge from sequential feature recovery.
problem Emergence of scaling laws from feature learning in multi-layer networks.
method Layer-wise spectral algorithm adapted to compositional structure, sequential feature detection.
result Sequential detection of latent features, leading to explicit power-law decay of prediction error.
In the framework of Lorentzian warped products, we study the Friedmann-Robertson-Walker cosmological model to investigate non-smooth curvatures associated with multiple discontinuities involved in the evolution of the universe. In particular we analyze non-smooth features of the spatially flat Friedmann-Robertson-Walke…
This work introduces two strategies for training network classifiers with heterogeneous agents. One strategy promotes global smoothing over the graph and a second strategy promotes local smoothing over neighbourhoods. It is assumed that the feature sizes can vary from one agent to another, with some agents observing in…
Spatial smoothing improves BNNs' accuracy, uncertainty, and robustness without increasing computational cost.
problem Large ensembles in BNNs increase computational cost and reduce performance.
method Spatial smoothing adds blur layers to convolutional neural networks to ensemble neighboring feature map points.
result Spatial smoothing improves BNNs' performance with fewer ensembles and enhances robustness.
Recent unsupervised approaches to domain adaptation primarily focus on minimizing the gap between the source and the target domains through refining the feature generator, in order to learn a better alignment between the two domains. This minimization can be achieved via a domain classifier to detect target-domain feat…
A new framework SIMBA improves graph classification performance on size-imbalanced datasets.
problem Size imbalance in graph classification leads to poor model performance.
method Energy-guided structural smoothing between head and tail graphs, re-weighting based on energy propagation.
result SIMBA outperforms existing methods in size-imbalanced graph classification tasks.
This paper selects features in deep neural networks with theoretical guarantees.
problem Feature selection in deep neural networks with unknown nonlinear functions.
method Reformulate neural networks as index models, estimate feature sets using Stein's formula, and apply screening-and-selection mechanism.
result Consistent feature selection with theoretical guarantees, even in high-dimensional settings.
New method makes neural network explanations more robust to attacks.
problem Vulnerability of feature attributions to adversarial attacks.
method Promotes Lipschitz continuity and smoothness in DNNs to improve robustness.
result Regularization and stochastic smoothing methods enhance attribution robustness.
We study submetries between Alexandrov spaces and show how some of the usual features of Riemannian submersions fail due to the lack of smoothness.
EML model tackles evolving features in online metric learning.
problem Challenges in applying metric learning to evolving features.
method Develops a new Evolving Metric Learning (EML) model for incremental and decremental features.
result EML model handles instance and feature evolutions simultaneously.
We study the fundamental problem of learning an unknown, smooth probability function via pointwise Bernoulli tests. We provide a scalable algorithm for efficiently solving this problem with rigorous guarantees. In particular, we prove the convergence rate of our posterior update rule to the true probability function in…
This paper analyzes kNN convergence over feature transformations.
problem The curse of dimensionality affects kNN performance in transformed feature spaces.
method Developed a novel analysis on kNN convergence rates over transformed features, linking properties of the transformed space to raw feature space.
result Theoretical analysis explains why some feature transformations are better for kNN.
In this paper we propose a function space approach to Representation Learning and the analysis of the representation layers in deep learning architectures. We show how to compute a weak-type Besov smoothness index that quantifies the geometry of the clustering in the feature space. This approach was already applied suc…
GHNet improves graph learning by balancing homogeneity and heterogeneity.
problem Over-smoothing in GCN leads to similar node representations.
method GHNet uses gating units to balance homogeneity and heterogeneity in feature propagation.
result GHNet achieves larger receptive fields without over-smoothing.
This paper considers the power of deep neural networks (deep nets for short) in realizing data features. Based on refined covering number estimates, we find that, to realize some complex data features, deep nets can improve the performances of shallow neural networks (shallow nets for short) without requiring additiona…
The paper investigates how Global Self-attention improves GCNs.
problem Improving expressive power and addressing overfitting in GCNs.
method Applying Global Self-attention mechanism over graph features.
result GSA mechanism enhances expressive power and mitigates overfitting and over-smoothing in GCNs.
Gradient descent with error feedback performs better than vanilla when features are rare.
problem Improving communication complexity in distributed optimization with rare features.
method Gradient descent with greedy sparsification and error feedback for rare features.
result Communication complexity improves as features become more rare, potentially better than vanilla GD.
A new method corrects weight values to improve treatment effect estimation.
problem Estimating heterogeneous treatment effects in high-dimensional data with sample selection bias.
method Differentiable Pareto-Smoothed Weighting (DPSW) framework.
result Our method outperforms existing methods in treatment effect estimation.
Deep neural networks with piecewise-polynomial activations can approximate smooth functions and their derivatives.
problem Approximating smooth functions and their derivatives with neural networks.
method Derives the depth, width, and sparsity required for approximation in Hölder norms.
result Deep neural networks with bounded weights can approximate Hölder smooth functions and their derivatives.
The paper investigates exotic smooth structures on manifolds with group actions.
problem Existence of homeomorphic but not diffeomorphic smooth manifolds with shared basic spectra.
method Investigates Riemannian Laplacian eigenvalues and eigenfunctions on manifolds with compact Lie group actions.
result Establishes the existence of homeomorphic yet not diffeomorphic manifolds with shared basic spectra.
We give elementary constructions of manifold with corner structures and associative gluing maps on compactifications of spaces of infinite, half infinite, and finite Morse flow lines.
Graph attention is not always beneficial; conditions for perfect node classification are identified.
problem Understanding when graph attention mechanisms improve node classification performance.
method Theoretical analysis using Contextual Stochastic Block Models (CSBMs).
result Graph attention mechanisms are more effective when structure noise exceeds feature noise, and simpler graph convolution operations are better when feature noise predominates.
We develop a 2D travel time tomography method which regularizes the inversion by modeling groups of slowness pixels from discrete slowness maps, called patches, as sparse linear combinations of atoms from a dictionary. We propose to use dictionary learning during the inversion to adapt dictionaries to specific slowness…
Robust feature-weighted jump models for time-dependent clustering
problem Temporal clustering
method Robust feature-weighted jump model
result Accurate recovery of true cluster sequence and feature identification
Nonparametric regression for massive numbers of samples (n) and features (p) is an increasingly important problem. In big n settings, a common strategy is to partition the feature space, and then separately apply simple models to each partition set. We propose an alternative approach, which avoids such partitioning and…
Efficiently solves Elastic Net in high dimensions with Newton method.
problem Feature selection in high-dimensional data with non-negligible collinearity.
method Semi-smooth Newton Augmented Lagrangian Method.
result Significantly reduces computational cost compared to competitors.
We develop a theory of parametrized geometric cobordism by introducing smooth Thom stacks. This requires identifying and constructing a smooth representative of the Thom functor acting on vector bundles equipped with extra geometric data, leading to a geometric refinement of the the Pontrjagin-Thom construction in stac…
New guarantees for Group LASSO in sparse convex optimization.
problem Sparse convex optimization with vector-valued features.
method Group LASSO regularization and analysis of gradient norms.
result Group LASSO selects the same features as Orthogonal Matching Pursuit.