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.
Paper improves forest representation learning by optimizing margin distribution.
problem Improving generalization gap in forest representation learning.
method Reformulated as an additive model, optimizing margin distribution ratio λ.
result Substantially improved upper bound of generalization gap from O(√(ln m / m)) to O((ln m) / m).
New DP algorithms with margin guarantees for various hypothesis sets.
problem Differential privacy in machine learning with margin guarantees.
method Developed pure and efficient DP learning algorithms for linear, kernel-based, and neural network hypotheses.
result Margin guarantees are independent of input dimension and hypothesis type.
Improved algorithm learns convex polyhedra with margin.
problem Learning convex polyhedra with margin in the realizable PAC setting.
method Constructs a consistent polyhedron as an intersection of halfspaces with constant-size margins.
result Polyhedra can be learned efficiently with margin constraints.
New private algorithms learn large-margin halfspaces efficiently.
problem Learning large-margin halfspaces with privacy constraints.
method Differentially private algorithms based on a new approach.
result Sample complexity depends only on the margin, not dimension.
Proposes a new distance metric for multi-marginal optimal transport.
problem Computational scalability in multi-marginal optimal transport.
method Random one-dimensional projections to construct sliced multi-marginal Wasserstein distance.
result Sliced multi-marginal Wasserstein distance is a metric with dimension-free sample complexity.
A new active learning method that improves model diversity and performance.
problem Efficiently selecting examples to label for training multiple models.
method Trains multiple models on bootstrap samples and selects examples based on minimum margin.
result Min-margin outperforms other methods, especially with larger batch sizes.
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.
Improves few-shot learning by adding a large margin to metric-based methods.
problem Few-shot learning's challenge of generalizing well with limited data.
method Unified framework with large margin distance loss function.
result Significant performance improvement with minimal computational overhead.
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.
Bayesian evidence helps compare models but can overfit.
problem Comparing hypotheses consistent with observations.
method Marginal likelihood, Occam's razor, PAC-Bayes bounds.
result Marginal likelihood can negatively correlate with generalization.
New theorem for deep neural networks improves classification margins.
problem Improving classification margins in deep neural networks.
method Local class-purity theorem and margin p-values for training and testing samples.
result Enhanced understanding and computation of classification margins.
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.
MACQ method explains deep learning models by analyzing feature contributions across prediction levels.
problem Explaining deep learning model predictions.
method Global gradient-based, model-agnostic approach focusing on marginal attribution.
result MACQ separates feature contributions from interaction effects and visualizes 3-way relationships.
Random projections have been applied in many machine learning algorithms. However, whether margin is preserved after random projection is non-trivial and not well studied. In this paper we analyse margin distortion after random projection, and give the conditions of margin preservation for binary classification problem…
New method estimates marginal likelihood for deep learning models using training data alone.
problem Estimation difficulties in marginal likelihood for model selection in deep learning.
method Scalable marginal likelihood estimation based on Laplace's method and Gauss-Newton approximations.
result Estimate outperforms cross-validation and manual tuning on various datasets.
Active learning can't improve over passive in certain settings.
problem Active learning vs. passive learning in nonparametric settings.
method Analyzing margin conditions and their effects on active learning performance.
result Nuances in margin conditions determine whether active learning can outperform passive learning.
New margin measure improves deep learning generalization and robustness.
problem Unclear relationship between output margin and generalization for deep models.
method Introduced 'all-layer margin' for deep neural networks.
result Tighter generalization bounds for neural nets with no exponential depth dependency.
New SVM margin bound improves generalization in machine learning.
problem Improving SVM margin bounds for better generalization.
method Stable sample compression schemes to derive new data-dependent generalization bounds.
result Proves a new optimal SVM margin bound with a log factor improvement.
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.
Learn invariances in models using the marginal likelihood.
problem Generalizing well in supervised learning tasks.
method Learn invariances in model structure using the marginal likelihood.
result Demonstrated for Gaussian process models, reducing complexity of invariant models.
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.
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.
MARVEL curbs memorization of noisy labels in deep nets.
problem Noisy labels degrade deep net performance.
method MARVEL tracks classification margins to identify and abandon noisy instances.
result MARVEL outperforms baselines on noisy datasets.
New method accelerates large margin metric learning for nearest neighbor classification.
problem Efficiently learning metrics for nearest neighbor classification.
method Triplet mining and stratified sampling for large margin metric learning.
result Improved efficiency and scalability of optimization.
Bayesian approach learns invariances from data alone, but last layer approximation is not always sufficient.
problem Learning invariances in neural networks using only training data.
method Bayesian marginal likelihood for last layer, custom optimisation routine, new lower bound.
result Partial success on standard benchmarks and medical imaging dataset, failure on CIFAR10.
Max-margin learning is a powerful approach to building classifiers and structured output predictors. Recent work on max-margin supervised topic models has successfully integrated it with Bayesian topic models to discover discriminative latent semantic structures and make accurate predictions for unseen testing data. Ho…
This paper proposes MMD-SVR to improve SVR's margin distribution for better generalization.
problem Improving SVR's generalization performance by maximizing the margin distribution of the whole dataset.
method Introducing MMD-SVR with coupled constraints to convert a non-convex optimization problem into a convex one.
result MMD-SVR significantly improves prediction accuracy and generalization compared to classic SVR.
We obtain a tight distribution-specific characterization of the sample complexity of large-margin classification with L2 regularization: We introduce the margin-adapted dimension, which is a simple function of the second order statistics of the data distribution, and show distribution-specific upper and lower bounds on…
AdaBoost's classifier and margins converge to a known value.
problem Convergence properties of AdaBoost algorithm.
method Formal proofs of convergence properties of AdaBoost's classifier and margins.
result AdaBoost's classifier and margins converge to a known value.
Large margin approach for deep neural networks.
problem Deep learning's lack of margin enforcement.
method Proposes a novel loss function to enforce margin across layers of deep networks.
result Improved performance on various datasets and tasks.
Maximizing margins leads to lossless compression of training data.
problem Generalization in supervised learning.
method Information-theoretic interpretation of margin maximization.
result Margin maximization is a form of lossless maximal compression.
An active margin system for margin loans is proposed for Chinese margin lending market, which uses cash and randomly selected stock as collateral. The conditional probability of negative return(CPNR) after a forced sale of securities from under-margined account in a falling market is used to measure the risk faced by t…
We address the problem of learning the parameters in graphical models when inference is intractable. A common strategy in this case is to replace the partition function with its Bethe approximation. We show that there exists a regime of empirical marginals where such Bethe learning will fail. By failure we mean that th…
Study how regularization and optimization affect margin in deep models.
problem Understanding margin maximization in deep learning models.
method Analyze the limit of loss minimization with diverging norm constraints and margin paths.
result Discovers lexicographic max-margin solutions for homogeneous models and shows convergence under certain conditions.
Study minimax rates for binary classifier estimation with margin conditions.
problem Estimating binary classifiers with geometric margin conditions.
method Derive lower bounds for worst-case learning rates over various function classes.
result Identify optimal rates close to O(n−1) for different function classes. Deep generative models (DGMs) are effective on learning multilayered representations of complex data and performing inference of input data by exploring the generative ability. However, it is relatively insufficient to empower the discriminative ability of DGMs on making accurate predictions. This paper presents max-ma…
A new approach for instance-optimal learning that bypasses impossibility results.
problem Impossibility of achieving marginal-by-marginal guarantees for all marginals.
method Introduces relatively smart learning, which requires competition only with certifiable semi-supervised guarantees.
result One-Inclusion Graph learner is relatively smart up to squaring the sample complexity.
Graphical models trained using maximum likelihood are a common tool for probabilistic inference of marginal distributions. However, this approach suffers difficulties when either the inference process or the model is approximate. In this paper, the inference process is first defined to be the minimization of a convex f…
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.
Framework for private, noise-tolerant, and efficient learning algorithms.
problem Private and efficient learning of large-margin halfspaces in noisy environments.
method Simple framework using differential privacy and noise tolerance conditions.
result Noise-tolerant and private PAC learners for large-margin halfspaces with sample complexity independent of dimension.
MLS improves feature selection for imbalanced data.
problem Machine learning challenges with imbalanced high-dimensional data.
method Introduces Marginal Laplacian Score (MLS) for better feature selection.
result MLS improves performance on synthetic and public datasets.
3MSBM learns smooth trajectories from multiple snapshots.
problem Capturing long-range temporal dependencies in complex systems.
method Lifts dynamics to phase space, generalizes stochastic bridges to multi-marginal conditional problems, learns transport maps preserving intermediate marginals.
result Significantly improves convergence and scalability in capturing complex dynamics.
We present a max-margin nonparametric latent feature model, which unites the ideas of max-margin learning and Bayesian nonparametrics to discover discriminative latent features for link prediction and automatically infer the unknown latent social dimension. By minimizing a hinge-loss using the linear expectation operat…
Given a matrix A, a linear feasibility problem (of which linear classification is a special case) aims to find a solution to a primal problem w:ATw>0 or a certificate for the dual problem which is a probability distribution p:Ap=0. Inspired by the continued importance of "large-margin cla…
ELM improves neural model embeddings for long-tail learning.
problem Learning skewed label distributions in neural models.
method Enforces margins in logit space and regularizes embedding distribution.
result ELM reduces generalization gap and tightens tail class embeddings.
Study evaluates margin parameter effects on knowledge embedding quality.
problem Understanding margin parameter's impact on embedding quality.
method Examined margin parameter values for multi-relational categorized data.
result Lower margin values are insufficient, while larger values cause noise.
A classical condition for fast learning rates is the margin condition, first introduced by Mammen and Tsybakov. We tackle in this paper the problem of adaptivity to this condition in the context of model selection, in a general learning framework. Actually, we consider a weaker version of this condition that allows one…