Proposes smoothing input and weight spaces for semi-supervised learning.
problem Improving semi-supervised learning performance with minimal data augmentation.
method Combines input-space and weight-space smoothing through adversarial optimization.
result Achieves comparable performance to state-of-the-art without heavy data augmentation.
This work uses sampling theory to analyze smoothness and error bounds of finite neural networks.
problem Analyzing the function space of finite neural networks and providing error bounds.
method Applying sampling theory to finite neural networks with non-expansive activation functions, considering both deterministic and random sampling.
result Novel error bounds for univariate neural networks under band-limited input assumption, highlighting the advantage of deterministic uniform sampling.
Deep learning performs well on high-dimensional data with anisotropic smoothness.
problem Understanding the performance of deep learning on high-dimensional datasets with varying smoothness.
method Investigated approximation and estimation errors in anisotropic Besov spaces.
result Deep learning's performance depends on the average smoothness, avoiding curse of dimensionality.
Input-dependent smoothing mitigates classical issues but suffers from the curse of dimensionality.
problem Certifiably robust classifiers with input-dependent smoothing suffer from the curse of dimensionality.
method Proposed a theoretical and practical framework for input-dependent smoothing under strict restrictions.
result Input-dependent smoothing mitigates some classical issues but is limited by the curse of dimensionality.
Randomized smoothing reduces accuracy in ML models, especially at higher noise levels.
problem Adversarial attacks on ML models, especially randomized smoothing's accuracy drop.
method Theoretical and empirical analysis of randomized smoothing's effect on feasible hypotheses space.
result For some noise levels, randomized smoothing shrinks the set of feasible hypotheses, leading to accuracy drops.
Novel framework improves randomized smoothing for various norms.
problem Developing robust defenses against adversarial attacks.
method Proposed a novel framework for devising and analyzing randomized smoothing schemes.
result Significantly improved certified accuracy in ℓ1 on standard datasets.
Enhances random forests by smoothing predictions for better performance.
problem Suboptimal performance due to piecewise constant predictions in random forests.
method Kernel-based smoothing mechanism to introduce local regularity.
result Smoothed random forest model consistently improves predictive performance.
New method enhances neural network robustness against adversarial attacks.
problem Enhancing neural network robustness against adversarial attacks.
method Variational framework with per-sample noise level selector.
result Enhanced empirical robustness and certified robustness.
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.
BOSS optimizes string inputs using string kernels and genetic algorithms.
problem Optimizing string inputs with constraints.
method Bayesian optimization over string kernels and genetic algorithms.
result Significantly improved optimization across various string constraints.
The paper derives error bounds for piecewise smooth and switching regression models.
problem Regression problems with target functions switching between different modes.
method Derives generalization error bounds using Rademacher complexities and chaining arguments.
result Error bounds with radical dependency on the number of modes for piecewise smooth regression, and linear dependency for switching regression.
DeformRS certifies deep networks against various input deformations.
problem Vulnerability of deep networks to input deformations.
method Randomized smoothing reformulation for general deformations.
result Certifies rich deformations including translations, rotations, scaling, and affine.
New findings show learning deeper neural networks is hard even with Gaussian inputs and non-degenerate weights.
problem The computational complexity of learning neural networks, especially deeper ones.
method Smoothed analysis framework and local pseudorandom generators.
result Learning depth-3 ReLU networks under Gaussian input distribution is hard even if weight matrices are non-degenerate.
We show that conically smooth stratified spaces embed fully faithfully into ∞-categories. This articulates a stratified generalization of the homotopy hypothesis proposed by Grothendieck. As such, each ∞-category defines a stack on conically smooth stratified spaces, and we identify the descent conditions…
The paper improves smoothed analysis for online problems with adaptive adversaries.
problem Online prediction, discrepancy minimization, and online optimization with adaptive adversaries.
method General technique to prove smoothed guarantees against adaptive adversaries, reducing to simpler oblivious adversaries.
result Strong smoothed guarantees for three online problems, matching or improving previous results.
Paper introduces a new regularization method for kernel gradient descent learning.
problem Preventing overfitting in kernel gradient descent learning.
method Random smoothing regularization as novel convolution-based smoothing kernels.
result Optimal convergence rates achieved in various function spaces.
New bounds explain deterministic non-smooth deep nets without large Lipschitz constants.
problem Challenges in explaining generalization of deterministic non-smooth deep nets.
method De-randomized PAC-Bayes margin bounds for deterministic non-convex and non-smooth predictors.
result New bounds avoid large Lipschitz constants, providing generalization guarantees.
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.
Cut-DeepONet handles discontinuities and sharp transitions in neural operators.
problem Neural operators struggle with discontinuities and sharp transitions in PDEs.
method Two-stage training framework that explicitly models discontinuities via a lifting strategy and input-dependent discontinuity prediction.
result Cut-DeepONet outperforms state-of-the-art methods on benchmark PDEs with low-resolution datasets.
Survey of generalized Kalman smoothing models and algorithms.
problem Efficient estimation of dynamic systems with outliers and abrupt changes.
method Replacing quadratic penalties with nonsmooth convex functions and using iterated algorithms.
result Generalized Kalman smoothing provides robust solutions for dynamic systems.
Transformer's attention mechanism is re-examined using kernel smoothing.
problem Understanding and optimizing the Transformer's attention mechanism.
method Presented a new kernel-based formulation of Transformer's attention mechanism.
result The new kernel-based formulation provides a better understanding of Transformer's attention components and introduces a new variant achieving competitive performance.
Derives moments of PL networks for robust DNNs.
problem Analyzing robustness of DNNs to adversarial attacks.
method Derives exact analytic expressions for moments of PL networks, generalizes variance expression, and constructs sparse and smooth adversarial attacks.
result New variance expressions are tighter and can be efficiently approximated.
A new SSL method improves medical image classification using global latent mixing.
problem Costly annotation of large-scale medical image data sets.
method Linear mixing of labeled and unlabeled data in both input and latent space.
result Improved performance in semi-supervised classification of thoracic disease and skin lesion.
A new method warps inputs to learn nonstationary kernels efficiently.
problem Learning nonstationary patterns in data with varying smoothness.
method Sparse spectrum Gaussian processes with input warping as conditional Gaussian measures.
result Efficient learning of nonstationary patterns with fewer parameters.
Extends randomized smoothing to certify robustness against various threat models and adversarial perturbations.
problem Certifying robustness of classifiers against adversarial perturbations.
method Develops a method to certify robustness against any ℓp (p∈N>0) minimized adversarial perturbation. result Randomized smoothing suffers from the curse of dimensionality, reducing effective radius as p increases. Proposes regularization for robust image models using Wasserstein geometry.
problem Robustness to in-class variations in input data.
method Wasserstein-2 geometry, Tikhonov-type regularizer, data augmentation.
result Improves generalization under adversarial perturbations and large variations.
Smoothness analysis of adversarial training reveals L∞ constraints cause more non-smoothness.
problem Non-smoothness of adversarial training loss function.
method Analyzed the smoothness of adversarial training loss function using optimal attacks for model parameters.
result The L∞ constraint causes more non-smoothness than L2 constraint. A new loss function improves deep learning performance without class separation constraints.
problem Training deep learning architectures for classification.
method Minimizing smoothness of label signals on similarity graphs.
result The proposed loss function leads to similar classification performance as cross-entropy, with added robustness.
Deep networks can interpolate noisy data without losing generalization.
problem Characterizing the relationship between interpolation and generalization in overparameterized deep networks.
method Analyzing the loss landscape of neural network functions over volumes around training data points, varying model parameters and training epochs.
result Loss sharpness in the input space follows a double descent, with large models predicting noisy targets over larger volumes around training data points.
Pairwise Label Smoothing improves deep model generalization by reducing overconfidence.
problem Improving deep model generalization through regularization.
method PLS smooths labels for pairs of samples, learning distribution mass during training.
result PLS significantly outperforms LS and baseline models, reducing up to 30% classification error.
We propose a novel adversarial training method in feature space that improves model robustness and computational efficiency.
problem Improving model robustness against adversarial input perturbations with computational efficiency.
method Shift from input to feature-space perturbations, reformulating the adversarial training problem in reproducing kernel Hilbert spaces, enabling exact solution of inner maximization and efficient optimization.
result The feature-perturbed formulation is a relaxation of the original problem and provides a regularized estimator that adapts to noise and function smoothness.
Vision transformers benefit from non-smooth components in adaptation.
problem Understanding the role of non-smoothness in vision transformer adaptation.
method Theoretical analysis and extensive experiments on large-scale vision transformers.
result High plasticity of attention modules and feedforward layers leads to better finetuning performance.
Paper shows SGD can learn RNNs efficiently for certain functions.
problem Understanding what concept class RNNs can learn and how efficiently.
method Vanilla stochastic gradient descent (SGD) approach.
result RNNs can learn some functions efficiently with polynomial complexity in input length.
Paper explains how tree ensembles improve predictions by smoothing and regulating smoothness.
problem Understanding why tree ensembles perform well despite their complexity.
method Interpreting tree ensembles as adaptive and self-regularizing smoothers.
result Ensemble trees make more smooth predictions than individual trees and adjust smoothness based on input dissimilarity.
Tensor completion method identifies nonlinear systems from input-output data.
problem Identifying nonlinear functions from input-output data pairs.
method Formulated as tensor completion problem with smoothness regularization and solved using block coordinate descent.
result Provable correct nonlinear system identification under certain conditions.
The paper establishes a continuous embedding between two types of Barron spaces in neural networks.
problem Understanding the relationship between two types of Barron spaces in neural networks.
method Introduced a continuous embedding inequality between Barron and spectral Barron spaces.
result The embedding inequality holds for any function in the spaces, with constants independent of the input dimension.
Study analyzes deep learning's performance on variable exponent Besov space, highlighting adaptivity benefits.
problem Estimation error analysis of deep learning in variable exponent Besov space.
method Analysis of general approximation error and estimation errors of deep learning.
result Adaptivity of deep learning leads to significant improvement in estimation error, especially in high-dimensional spaces.
New algorithm learns halfspaces over hypercube with random bit flips.
problem Agnostic learning of Boolean halfspaces over discrete domains is computationally hard.
method Smoothed analysis with random bit flips for discrete inputs.
result First efficient algorithm for smoothed agnostic learning of halfspaces over Boolean hypercube.
Smoothly prepares quantum states for robust machine learning.
problem Efficiently preparing quantum states for machine learning.
method Smoothed analysis to prove constant query state preparation.
result State preparation can be achieved with constant queries under realistic noise conditions.
New method improves certified robustness for classifier confidence.
problem Certifying confidence in classifier predictions.
method Randomized smoothing with modified Neyman-Pearson lemma.
result Certified radii for prediction confidence improved.
Develops new oracle inequalities for Gaussian ranking estimators.
problem Lack of rigorous theoretical support for Gaussian ranking estimators.
method Novel oracle inequalities for regularized pairwise ranking.
result Derives fast learning rates under general dimension assumptions.
Enhances robustness of deep neural networks with randomized smoothing.
problem Improving robustness of deep neural networks against noisy inputs and adversarial attacks.
method Introduces a variance-margin trade-off approach to increase certified robust radius using pre-trained models.
result Significant improvement in certified accuracy compared to state-of-the-art methods.
Estimates convex hulls of smooth function images with error bounds.
problem Estimating the convex hull of the image of a smooth boundary set.
method Using submersion properties and sampling inputs, derive bounds on Hausdorff distance.
result New tighter and more general error bounds for geometric inference.
Auto-regressive models improve smoothing efficiency with exponentially tapered windows.
problem Improving time-series smoothing efficiency.
method An auto-regressive formulation for time-series smoothing.
result Auto-regressive models result in moving means with exponentially tapered windows.
Neural network predicts functional responses from scalar inputs.
problem Regression of functional responses with large scalar predictors and nonlinear relationships.
method Transform functional response to finite dimensions, design feed-forward neural network, modify output via objective functions, apply roughness penalty.
result Proposed neural network outperforms conventional methods in multiple scenarios.
DropEdge improves deep GCNs for node classification by reducing over-fitting and over-smoothing.
problem Over-fitting and over-smoothing in deep GCNs for node classification.
method Randomly removes edges from the input graph at each training epoch to reduce over-fitting and over-smoothing.
result DropEdge improves performance on various GCN models and prevents over-smoothing.
RS-Del provides robustness for sequence classifiers against edit distance attacks.
problem Certifying robustness of discrete sequence classifiers against edit distance attacks.
method Randomized deletion (RS-Del) for discrete sequence classifiers, focusing on edit distance-bounded adversaries.
result Achieved a certified accuracy of 91% at an edit distance radius of 128 bytes on malware detection.
Fusion of robustness and uncertainty techniques improves adversarial defense.
problem Adversarial attacks on deep neural networks.
method Integrating uncertainty quantification into randomized smoothing for robustness guarantees.
result Improved robustness guarantees for uncertainty aware classifiers.