New loss function improves convergence rate for neural networks.
problem Improving convergence speed of neural networks for classification tasks.
method Proposes a modified hinge loss function with gradients to critical points.
result Margin converges to max-margin at O(1/t) rate, faster than exponential losses. 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.
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.
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.
We analyze bias-variance of margin losses.
problem Understanding model overfitting/underfitting.
method Bias-variance decomposition for strictly convex margin losses.
result Expected risk decomposes into central model risk and data variation.
Gradient descent converges to max-margin solution for hinge loss.
problem Applying gradient descent to the hinge loss for linear classifiers.
method Homotopic gradient descent applied to the hinge loss.
result Explicit convergence rates to max-margin solution for separable data.
Proposes AML loss function for TransE to improve link prediction in knowledge graphs.
problem Low performance of TransE due to insufficient scores of positive triples.
method Introduces Adaptive Margin Loss (AML) to automatically adjust margin during training.
result AML improves TransE's performance on link prediction tasks in knowledge graphs.
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.
This paper studies Fenchel-Young losses, a generic way to construct convex loss functions from a regularization function. We analyze their properties in depth, showing that they unify many well-known loss functions and allow to create useful new ones easily. Fenchel-Young losses constructed from a generalized entropy, …
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.
Proposes SOVR loss to improve adversarial robustness by increasing logit margins.
problem Adversarial training's difficulty in robustness against sophisticated attacks.
method Introduces SOVR loss function that switches from cross-entropy to one-vs-the-rest loss for important samples.
result SOVR loss increases logit margins of important samples, improving robustness against Auto-Attack.
Study compares metric learning loss functions for speaker verification.
problem Comparing metric learning loss functions for end-to-end speaker verification.
method Cross entropy loss, cosine loss, angular margin loss, center loss, contrastive loss, triplet loss.
result Additive angular margin loss outperforms other loss functions.
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…
Paper improves deep neural networks' generalization by focusing on margin distribution complexity.
problem Improving deep neural networks' generalization performance.
method Proves a generalization upper bound based on margin distribution statistics and optimizes a convex margin distribution loss function.
result Optimizing the ratio of margin standard deviation to expected margin enhances generalization performance.
We present a formulation of deep learning that aims at producing a large margin classifier. The notion of margin, minimum distance to a decision boundary, has served as the foundation of several theoretically profound and empirically successful results for both classification and regression tasks. However, most large m…
The paper proposes effective margin regularization to improve adversarial robustness in deep neural networks.
problem Adversarial vulnerability of deep neural networks (DNNs).
method Regularization of effective weight norm during training to maximize effective margins.
result Effective margin regularization (EMR) boosts adversarial robustness in both standard and adversarial training.
The key issue of few-shot learning is learning to generalize. This paper proposes a large margin principle to improve the generalization capacity of metric based methods for few-shot learning. To realize it, we develop a unified framework to learn a more discriminative metric space by augmenting the classification loss…
We analyze the semi-hard triplet loss using Edgeworth expansion for better understanding of its behavior.
problem Understanding the behavior of the semi-hard triplet loss function.
method Developed a higher-order asymptotic analysis using the Edgeworth expansion.
result Derived explicit Edgeworth expansions revealing first-order corrections in terms of the third cumulant.
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…
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…
We study losses for binary classification and class probability estimation and extend the understanding of them from margin losses to general composite losses which are the composition of a proper loss with a link function. We characterise when margin losses can be proper composite losses, explicitly show how to determ…
We provide a detailed study on the implicit bias of gradient descent when optimizing loss functions with strictly monotone tails, such as the logistic loss, over separable datasets. We look at two basic questions: (a) what are the conditions on the tail of the loss function under which gradient descent converges in the…
We study the implicit bias of gradient descent methods in solving a binary classification problem over a linearly separable dataset. The classifier is described by a nonlinear ReLU model and the objective function adopts the exponential loss function. We first characterize the landscape of the loss function and show th…
We propose the Margin Adaptation for Generative Adversarial Networks (MAGANs) algorithm, a novel training procedure for GANs to improve stability and performance by using an adaptive hinge loss function. We estimate the appropriate hinge loss margin with the expected energy of the target distribution, and derive princi…
In binary classification problems, mainly two approaches have been proposed; one is loss function approach and the other is uncertainty set approach. The loss function approach is applied to major learning algorithms such as support vector machine (SVM) and boosting methods. The loss function represents the penalty of …
New risk bound derived for multi-category margin classifiers.
problem Guaranteed risk dependency on categories, sample size, and margin parameter.
method Derived a new risk bound using Rademacher complexity and chaining method.
result Improved dependency on categories over state of the art.
Paper corrects Max-Margin loss for multi-label tasks.
problem Max-Margin loss inconsistency in multi-label classification.
method Introduced Restricted-Max-Margin loss.
result Consistent loss for multi-label tasks under milder conditions.
We exhibit a strong link between frequentist PAC-Bayesian risk bounds and the Bayesian marginal likelihood. That is, for the negative log-likelihood loss function, we show that the minimization of PAC-Bayesian generalization risk bounds maximizes the Bayesian marginal likelihood. This provides an alternative explanatio…
Advances robustness of metric learning by adversarial margin in input space.
problem Improving robustness of metric learning algorithms.
method Imposing adversarial margin in input space, minimizing perturbation loss.
result Enlarged adversarial margin improves generalization and robustness.
The paper proposes a framework for structured prediction using projection oracles.
problem Structured prediction with improved loss functions.
method A general framework for deriving loss functions using convex sets and projection oracles.
result Projections onto the marginal polytope can make the loss smaller and are computationally efficient.
Mirror flow optimizes separable data problems, converging to a maximum margin classifier.
problem Optimizing classification problems with separable data using mirror flow.
method Examine mirror flow on linearly separable classification problems, focusing on the horizon function of the mirror potential.
result Mirror flow converges to a maximum margin classifier for separable data under certain conditions.
Paper introduces negative margin loss for better few-shot classification accuracy.
problem Improving few-shot classification accuracy with metric learning.
method Introduces negative margin loss and analyzes its impact on feature discriminability.
result Negative margin loss outperforms regular softmax loss on few-shot classification benchmarks.
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…
New framework for learning from imbalanced data with theoretical guarantees.
problem Class imbalance in machine learning, especially in multi-class problems.
method Theoretical framework and new margin loss function for imbalanced classification.
result Proves strong H-consistency of the proposed margin loss function. 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. New insights into deep learning: reducing training data significantly improves performance.
problem Understanding and improving generalization in deep learning models.
method Analyzing the distribution of classification margins and dynamically reducing the training set.
result The area under the curve of the margin distribution is a good measure of generalization.
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 DAM method improves AUC scores in medical image classification.
problem Maximizing AUC in large-scale medical image classification.
method Proposes AUC margin loss for robust optimization, conducts extensive empirical studies.
result Improves performance on four medical image classification tasks, achieving 1st place on Stanford CheXpert.
Improved robustness of machine learning models with controlled Lipschitz constants.
problem Vulnerability of state-of-the-art models to adversarial attacks.
method Proposes a CLL loss that calibrates the margin and Lipschitz constant penalties, improving robustness certificates.
result Consistently outperforms other losses on CIFAR-10, CIFAR-100, and Tiny-ImageNet datasets.
Given a task of predicting Y from X, a loss function L, and a set of probability distributions Γ on (X,Y), what is the optimal decision rule minimizing the worst-case expected loss over Γ? In this paper, we address this question by introducing a generalization of the principle of maximum entropy. Applying t…
We carefully study how well minimizing convex surrogate loss functions, corresponds to minimizing the misclassification error rate for the problem of binary classification with linear predictors. In particular, we show that amongst all convex surrogate losses, the hinge loss gives essentially the best possible bound, o…
This paper introduces new loss functions for balanced multi-class classification.
problem Balancing class imbalance in multi-class classification.
method Introduces two new surrogate loss families: GLA and GCA.
result GCA losses offer stronger theoretical guarantees in imbalanced settings.
New measure predicts deep networks' generalization gap from margin distributions.
problem Predicting deep networks' generalization gap from training data.
method Proposes a measure based on margin distribution across multiple layers.
result Proposed measure correlates strongly with generalization gap on CIFAR datasets.
Improved SincNet for better speaker recognition.
problem Speaker recognition challenges and the need for better deep learning models.
method Proposes AM-SincNet, a SincNet-based model with an improved AM-Softmax layer.
result Improved speaker recognition performance, achieving a 40% Frame Error Rate reduction.
This work provides bounds on the performance of prediction models in the predict-then-optimize framework.
problem Generalizing the performance of prediction models in the predict-then-optimize framework with the SPO loss function.
method Deriving generalization bounds using the Natarajan dimension and exploiting the strength property of the feasible region.
result Improved generalization bounds for the SPO loss function, scaling logarithmically in the number of extreme points and linearly in the decision dimension.
Support vector machines (SVMs) naturally embody sparseness due to their use of hinge loss functions. However, SVMs can not directly estimate conditional class probabilities. In this paper we propose and study a family of coherence functions, which are convex and differentiable, as surrogates of the hinge function. The …
Paper proposes adaptive margin loss to improve few-shot learning.
problem Few-shot learning's difficulty in generalizing from a few examples.
method Develops class-relevant and task-relevant additive margin losses.
result Boosts performance of metric-based meta-learning approaches.
Gradient descent finds halfspaces with low error for agnostic learning.
problem Agnostic learning of linear halfspaces with convex surrogates.
method Gradient descent on convex surrogates for zero-one loss.
result Gradient descent finds halfspaces with error O(OPT1/2+ε) in poly time and sample complexity.