New margin-based learning guarantees improve generalization bounds.
problem Improving generalization bounds for machine learning models.
method Relative deviation margin bounds using empirical margin loss and Rademacher complexity.
result Distribution-dependent generalization bounds for unbounded loss functions.
New bound on neural network generalization error using geometric complexity.
problem Understanding the generalization capabilities of deep neural networks.
method Derive a new upper bound on generalization error using margin-normalized geometric complexity.
result Empirical validation of the bound for ResNet-18 on CIFAR-10 and CIFAR-100 datasets.
The paper improves SVM margin-based generalization bounds.
problem Improving generalization bounds for SVMs.
method Revisiting and improving classic generalization bounds in terms of margins, complementing with a nearly matching lower bound.
result Almost settles the generalization performance of SVMs in terms of margins.
New margin bound improves generalization for voting classifiers.
problem Improving generalization bounds for voting classifiers.
method Established a new margin-based generalization bound.
result Derives an optimal weak-to-strong learner with matching theoretical lower bound.
We present a simple noise-robust margin-based active learning algorithm to find homogeneous (passing the origin) linear separators and analyze its error convergence when labels are corrupted by noise. We show that when the imposed noise satisfies the Tsybakov low noise condition (Mammen, Tsybakov, and others 1999; Tsyb…
Study generalization of voting classifiers using margin-based bounds.
problem Understanding the generalization of ensemble classifiers like voting.
method Proved margin-based generalization bounds using PAC-Bayes theory and Dirichlet posteriors.
result Provided state-of-the-art guarantees on classification tasks.
Develops active learning method for linear optimization with margin-based criterion.
problem Optimizing decisions in linear optimization problems with limited labeled data.
method Smart Predict-then-Optimize (SPO) loss and margin-based active learning algorithm.
result Algorithm achieves significantly fewer labels than naive supervised learning, especially for minimizing SPO loss.
New lower bounds nearly match existing upper bounds for boosted classifiers.
problem Understanding the generalization performance of boosted classifiers.
method Margin-based lower bounds on boosted classifiers.
result Lower bounds nearly match the kth margin bound, settling the generalization performance of boosted classifiers. New margin-based regularization and selective sampling improve deep neural network performance.
problem Improving deep neural network performance on various classification tasks.
method Multi-margin regularization (MMR) and minimal margin score (MMS) for selective sampling.
result Improved results on multiple classification tasks across domains.
Paper studies statistical properties of DP data synthesis algorithms based on Bayesian networks.
problem Ensuring differential privacy in synthetic data generation for high-dimensional data.
method Introduces random noise to low-dimensional marginals of a probabilistic graphical model (BN) to achieve differential privacy.
result Establishes a rigorous accuracy guarantee for BN-based DP synthetic data generators using total variation (TV) distance.
Consider a classification problem where we have both labeled and unlabeled data available. We show that for linear classifiers defined by convex margin-based surrogate losses that are decreasing, it is impossible to construct any semi-supervised approach that is able to guarantee an improvement over the supervised clas…
We use surrogate losses to obtain several new regret bounds and new algorithms for contextual bandit learning. Using the ramp loss, we derive new margin-based regret bounds in terms of standard sequential complexity measures of a benchmark class of real-valued regression functions. Using the hinge loss, we derive an ef…
New bounds show neural networks can resist attacks better with sparse weights.
problem Neural networks are vulnerable to small adversarial perturbations.
method Compression based on effective sparsity and joint sparsity.
result Neural networks with approximately sparse weight matrices have better robustness and generalization.
New method prevents class collapse in metric learning with margin-based losses.
problem Class collapse in metric learning due to diverse intra-class samples.
method Proposed a sampling method to select nearest same-class samples as positive elements in tuple.
result Demonstrated clear benefits on various fine-grained image retrieval datasets.
A new loss function α-loss bridges log-loss and 0-1 loss for binary classification.
problem Improving binary classification performance using a tunable loss function.
method Introducing α-loss, proving its margin-based form and classification-calibration, and providing an upper bound on empirical risk. result Empirical and expected risk difference upper bound for logistic regression-based classification.
PrAda-GAN improves synthetic data generation under differential privacy.
problem Generating synthetic data under differential privacy with marginal-based methods.
method Sequential generator architecture integrating GAN and marginal-based approaches, with adaptive regularization of Bayes network structure.
result PrAda-GAN outperforms existing methods in privacy-utility trade-off on synthetic and real-world datasets.
New algorithm improves online multiclass classification with partial feedback.
problem Online multiclass classification with partial feedback.
method Inspired by complementary labels, a margin-based deterministic approach.
result Our method outperforms existing non-margin-based and stochastic methods.
Improves GATs by adding margin-based constraints to prevent over-fitting and over-smoothing.
problem Over-fitting and over-smoothing in GATs.
method Margin-based constraints on attention weights and graph structure.
result Significant improvements over previous GATs on various datasets.
This paper presents a margin-based multiclass generalization bound for neural networks that scales with their margin-normalized "spectral complexity": their Lipschitz constant, meaning the product of the spectral norms of the weight matrices, times a certain correction factor. This bound is empirically investigated for…
Residuals improve deep neural networks without increasing hypothesis complexity.
problem Understanding how residual connections affect hypothesis complexity and generalization.
method Analyzing the covering number of the hypothesis space and deriving a margin-based generalization bound.
result Residual connections do not increase the hypothesis complexity of neural networks.
Linear-Core Surrogates combine fast optimization and statistical efficiency in classification and structured prediction.
problem The trade-off between smoothness and margin-based losses in classification and structured prediction.
method Linear-Core (LC) Surrogates, a family of convex loss functions that stitch a linear core to a smooth tail.
result LC Surrogates achieve fast linear consistency rates while maintaining differentiability and strict H-consistency bounds. We establish a margin based data dependent generalization error bound for a general family of deep neural networks in terms of the depth and width, as well as the Jacobian of the networks. Through introducing a new characterization of the Lipschitz properties of neural network family, we achieve significantly tighter g…
Paper explores connections between loss functions and consistency in binary classification and regression.
problem Consistency in binary classification and regression applications.
method Characterization of conformable loss functions and derivation of a new Huber-type loss function.
result Margin-based loss functions are equivalent to loss functions of squared standardized logistic regression residuals.
We present surrogate regret bounds for arbitrary surrogate losses in the context of binary classification with label-dependent costs. Such bounds relate a classifier's risk, assessed with respect to a surrogate loss, to its cost-sensitive classification risk. Two approaches to surrogate regret bounds are developed. The…
Develops bounds predicting deep learning generalization using optimal transport.
problem Discrepancy between theoretical error bounds and empirical observations in deep learning.
method Margin-based generalization bounds with optimal transport costs.
result Theoretical bounds robustly predict generalization error on large datasets.
Optimized deferral improves accuracy in imbalanced settings.
problem Imbalance in expert predictions leads to suboptimal performance in two-stage learning to defer.
method Developed novel cost-sensitive learning algorithms and margin-based loss functions tailored for expert imbalance.
result MILD algorithm shows clear improvements over baselines in image classification and LLM routing tasks.
New findings show margins are not sufficient for explaining gradient boosting performance.
problem The inadequacy of margin explanations in explaining the performance of gradient boosting.
method Demonstrated and proved a stronger margin-based generalization bound for boosted classifiers.
result Proved a stronger margin-based generalization bound that explains the performance of modern gradient boosters.
We present a method to stop the evaluation of a decision making process when the result of the full evaluation is obvious. This trait is highly desirable for online margin-based machine learning algorithms where a classifier traditionally evaluates all the features for every example. We observe that some examples are e…
We address the problem of aggregating an ensemble of predictors with known loss bounds in a semi-supervised binary classification setting, to minimize prediction loss incurred on the unlabeled data. We find the minimax optimal predictions for a very general class of loss functions including all convex and many non-conv…
Margin-based classifiers have been popular in both machine learning and statistics for classification problems. Since a large number of classifiers are available, one natural question is which type of classifiers should be used given a particular classification task. We answer this question by investigating the asympto…
New algorithms recover clusters with minimal queries, connecting margins to recoverability.
problem Active cluster recovery with oracle queries for minimal cost.
method Introducing margin-based clustering, designing algorithms for various spaces.
result Achieve O(logn) queries for general pseudometric spaces and convex clusters. Unified binary and multiclass margin-based classification methods.
problem No consensus on multiclass loss functions analogous to binary margin loss.
method Showed multiclass loss functions can be expressed in relative margin form.
result Extended classification-calibration result to multiclass.
The standard margin-based structured prediction commonly uses a maximum loss over all possible structured outputs. The large-margin formulation including latent variables not only results in a non-convex formulation but also increases the search space by a factor of the size of the latent space. Recent work has propose…
Sine activation functions enable two-layer neural networks to learn modular addition more efficiently.
problem Learning modular addition with two-layer neural networks.
method Introduced and analyzed sine activation functions, providing theoretical and empirical evidence.
result Sine activation functions allow for constant-width network realizations of modular addition, whereas ReLU networks require linear width scaling.
Paper establishes a universal growth rate for smooth surrogate losses in classification.
problem Analyzing growth rates of consistency bounds for various surrogate losses.
method Proves square-root growth rate for smooth margin-based losses; extends to multi-class classification.
result Demonstrates a universal square-root growth rate for smooth comp-sum and constrained losses.
A new method accelerates deep neural network training using minimal margin score.
problem Training deep neural networks is computationally expensive.
method Introduces minimal margin score (MMS) for selecting samples.
result Significant acceleration in training deep neural networks.
New method improves consistency in preference learning for neural networks.
problem Inconsistent surrogate losses in preference learning for neural networks.
method Formulated a margin-shifted ranking framework and introduced Structure-Aware H-consistency. result Proved superior consistency guarantees for capacity-bounded models using heavy-tailed surrogates.
Margin-based structured prediction commonly uses a maximum loss over all possible structured outputs \cite{Altun03,Collins04b,Taskar03}. In natural language processing, recent work \cite{Zhang14,Zhang15} has proposed the use of the maximum loss over random structured outputs sampled independently from some proposal dis…
A preference order or ranking aggregated from pairwise comparison data is commonly understood as a strict total order. However, in real-world scenarios, some items are intrinsically ambiguous in comparisons, which may very well be an inherent uncertainty of the data. In this case, the conventional total order ranking c…
Classification is an important statistical learning tool. In real application, besides high prediction accuracy, it is often desirable to estimate class conditional probabilities for new observations. For traditional problems where the number of observations is large, there exist many well developed approaches. Recentl…
OSAMD adapts online to changing distributions with limited labels.
problem Models struggle with continual distribution shifts and expensive labeling in changing environments.
method Online Active Continual Adaptation with OSAMD, an online teacher-student structure and margin-based criterion.
result OSAMD achieves favorable dynamic regret bounds under changing environments with limited labels.
Relief based algorithms have often been claimed to uncover feature interactions. However, it is still unclear whether and how interaction terms will be differentiated from marginal effects. In this paper, we propose IMMIGRATE algorithm by including and training weights for interaction terms. Besides applying the large …
New methods improve deep learning on imbalanced datasets.
problem Poor performance of deep learning on imbalanced datasets.
method Label-distribution-aware margin (LDAM) loss and a training schedule.
result Combination of methods achieves significant performance gains.
Paper establishes comparison theorems for large-margin learning.
problem Data piling issue in high-dimension and low-sample size SVM.
method Large-margin unified machines (LUM) loss functions.
result New comparison theorems for all LUM loss functions.
New research shows SVM and related methods can overfit without harm in multiclass classification.
problem Understanding benign overfitting in multiclass classification.
method Analyzing three training algorithms: ERM with cross-entropy, least-squares, and one-vs-all SVM.
result All three algorithms can lead to classifiers that interpolate training data and have equal accuracy under high overparameterization.
Proposes adaptive method for classifying interval-valued time series.
problem Lack of classification methods for interval-valued time series.
method Represent intervals as images, classify using CNN, optimize coefficients with ADMM.
result Validated through simulations and real data, outperforming point-valued methods.
This work explores the relationship between expressivity and generalization in GNNs.
problem Understanding the trade-off between expressivity and generalization in GNNs.
method Introducing a novel framework that connects GNN generalization to the variance in graph structures they can capture.
result Theoretical findings align with empirical results, offering a deeper understanding of how expressivity enhances GNN generalization.
Learning a regression function using censored or interval-valued output data is an important problem in fields such as genomics and medicine. The goal is to learn a real-valued prediction function, and the training output labels indicate an interval of possible values. Whereas most existing algorithms for this task are…