Gradient descent and SGD can converge to max-margin directions in ReLU models.
problem Understanding the implicit bias of gradient methods in ReLU models.
method Characterization of loss function landscape, analysis of GD and SGD convergence, exploration of multi-neuron network learning.
result Gradient descent and SGD can converge to max-margin directions in ReLU models.
Adam's bias shifts from full-batch to max-margin of different norms for separable data.
problem Understanding Adam's implicit bias in the incremental batch setting.
method Analyzing incremental Adam on linearly separable data, constructing datasets, and using a proxy algorithm.
result Incremental Adam can converge to different max-margin classifiers depending on the dataset and batching scheme.
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…
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.
Max-margin classifiers' behavior is studied in high dimensions with non-Gaussian features.
problem Understanding the role of featurization maps and high-dimensional misclassification error.
method High-dimensional asymptotics, Gaussian model, support vector representation.
result Asymptotic behavior of max-margin classifiers is determined by feature covariance and label covariance.
We consider the problem of discriminative factor analysis for data that are in general non-Gaussian. A Bayesian model based on the ranks of the data is proposed. We first introduce a new {\em max-margin} version of the rank-likelihood. A discriminative factor model is then developed, integrating the max-margin rank-lik…
Paper analyzes GMM for separable data with various parameter structures.
problem Classifying separable data with logistic models and their generalizations.
method Introduces and analyzes Generalized Margin Maximizer (GMM) for logistic models with specific parameter structures.
result GMM outperforms max-margin classifiers in various parameter settings and structures.
Interpolation hurts robust generalization even without noise.
problem The challenge of robust generalization in the absence of noise.
method Avoiding interpolation through ridge regularization.
result Ridge regularization improves robust generalization.
Max-margin classifiers can overfit without harming performance in high dimensions.
problem Understanding how max-margin classifiers generalize in high-dimensional settings.
method Stylized setting with Gaussian features and labels, proportional asymptotics, and random neural network features.
result Exact expressions for limiting generalization error and conditions for 'benign overfitting'.
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…
Paper proposes MDAT to stabilize domain alignment in label-scarce settings.
problem Stable and comprehensive domain alignment in label-scarce settings.
method Max-margin Domain-Adversarial Training (MDAT) with Adversarial Reconstruction Network (ARN).
result MDAT stabilizes gradient reversing and achieves strong robustness to hyper-parameters.
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.
Theory for soft-margin classifiers on object manifolds.
problem Classifying object manifolds with variability.
method Mean-field theory of soft-margin classifiers applied to object manifolds.
result Prediction of classification errors and their dependence on regularization.
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 tackles multi-label zero-shot learning, improving label embedding projection for unseen classes.
problem Challenges in transferring knowledge from seen to unseen classes in multi-label zero-shot learning.
method Proposes a transfer-aware embedding projection approach to project label embeddings into a low-dimensional space for better inter-label relationships and explicit information transfer.
result Demonstrates the efficacy of the proposed approach through experiments on zero-shot multi-label image classification.
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…
A deep generative model is developed for representation and analysis of images, based on a hierarchical convolutional dictionary-learning framework. Stochastic {\em unpooling} is employed to link consecutive layers in the model, yielding top-down image generation. A Bayesian support vector machine is linked to the top-…
New findings on the max margin problem in neural networks.
problem Understanding the max margin problem in neural networks.
method Analyzing gradient flow and max margin problem in linear and ReLU networks.
result The KKT point is not always an optimum of the max margin problem.
Algorithm improves SVM classification in non-Euclidean spaces.
problem Limitations of traditional SVM in non-Euclidean spaces.
method Covariance-adjusted SVM using Cholesky Decomposition.
result Cholesky-SVM outperforms traditional SVM in non-Euclidean spaces.
New findings on robust learning with well-separated data.
problem Learning robust classifiers with well-separated classes.
method Analyzing sample complexity for linear classifiers with robustness.
result For linear classifiers on well-separated data, robust loss is at least $Ω( rac{d}{n})$.
Link prediction is a fundamental task in statistical network analysis. Recent advances have been made on learning flexible nonparametric Bayesian latent feature models for link prediction. In this paper, we present a max-margin learning method for such nonparametric latent feature relational models. Our approach attemp…
Model reveals double descent in binary linear classification.
problem Investigating classification error in high-dimensional binary linear classification.
method Gradient descent on logistic loss, maximum-likelihood, max-margin (SVM) solutions, and convex Gaussian min-max theorem.
result Double descent phenomenon observed in classification error for varying overparameterization ratio.
Bayesian max-margin models have shown superiority in various practical applications, such as text categorization, collaborative prediction, social network link prediction and crowdsourcing, and they conjoin the flexibility of Bayesian modeling and predictive strengths of max-margin learning. However, Monte Carlo sampli…
In this paper we propose an approach to preference elicitation that is suitable to large configuration spaces beyond the reach of existing state-of-the-art approaches. Our setwise max-margin method can be viewed as a generalization of max-margin learning to sets, and can produce a set of "diverse" items that can be use…
A new method for unsupervised domain adaptation using Gaussian processes.
problem Reducing target domain error by aligning input and output distributions.
method Max-margin Gaussian process approach to achieve hypothesis consistency.
result Our method effectively minimizes maximum discrepancy and maximizes margins.
GMC benchmark isolates retrieval in Transformers, revealing max-margin alignment.
problem Understanding how Transformers develop match-and-copy behavior on natural data.
method Introducing Gaussian Match-and-Copy (GMC) as a minimalist benchmark.
result Gradient descent drives parameters to diverge while aligning with max-margin separator.
AUC (Area under the ROC curve) is an important performance measure for applications where the data is highly imbalanced. Learning to maximize AUC performance is thus an important research problem. Using a max-margin based surrogate loss function, AUC optimization problem can be approximated as a pairwise rankSVM learni…
Supervised topic models utilize document's side information for discovering predictive low dimensional representations of documents. Existing models apply the likelihood-based estimation. In this paper, we present a general framework of max-margin supervised topic models for both continuous and categorical response var…
Images seen during test time are often not from the same distribution as images used for learning. This problem, known as domain shift, occurs when training classifiers from object-centric internet image databases and trying to apply them directly to scene understanding tasks. The consequence is often severe performanc…
Adaptive kernel model for multi-view learning reduces overfitting and scales with data.
problem Overfitting and high computational cost in multi-view learning.
method Bayesian framework, Dirichlet process Gaussian mixtures, random Fourier features, max-margin constraints, MCMC sampler.
result Adaptive learning of shift-invariant kernels from data.
We propose Very Simple Classifier (VSC) a novel method designed to incorporate the concepts of subsampling and locality in the definition of features to be used as the input of a perceptron. The rationale is that locality theoretically guarantees a bound on the generalization error. Each feature in VSC is a max-margin …
Max-min margin Markov networks improve consistency in structured prediction.
problem Statistical inconsistency in max-margin methods for structured prediction.
method Defining a max-min margin formulation to overcome statistical inconsistency.
result Proves consistency and provides an explicit algorithm with finite sample generalization bounds.
Our paper examines binary linear classification under Gaussian mixtures, revealing conditions for optimal performance.
problem Understanding the conditions for optimal performance of binary linear classifiers under Gaussian mixtures.
method We study max-margin SVM and min-norm interpolating classifiers, deriving bounds and conditions for optimal performance.
result Interpolating estimators achieve asymptotically optimal performance under certain conditions, emphasizing the role of SNR and covariance.
GD at EoS edge minimizes logistic loss without monotonic convergence.
problem Understanding GD's implicit bias at the edge of stability.
method Theoretical analysis of logistic regression with constant stepsize GD.
result GD with any constant stepsize minimizes logistic loss over long time scales.
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.
Analysis of gradient descent on wide neural networks reveals strong generalization.
problem Understanding why wide neural networks trained with logistic loss perform well.
method Characterization of gradient flow limits and comparison to max-margin classifier.
result Margin is independent of ambient dimension, leading to strong generalization.
Currently, machine learning plays an important role in the lives and individual activities of numerous people. Accordingly, it has become necessary to design machine learning algorithms to ensure that discrimination, biased views, or unfair treatment do not result from decision making or predictions made via machine le…
Gradient methods avoid overfitting on separable data.
problem Overfitting on separable data with gradient methods.
method Gradient methods (flow, descent, SGD) on separable data.
result Gradient methods asymptotically do not overfit on separable data.
Word embeddings provide point representations of words containing useful semantic information. We introduce multimodal word distributions formed from Gaussian mixtures, for multiple word meanings, entailment, and rich uncertainty information. To learn these distributions, we propose an energy-based max-margin objective…
New tensor formulation reveals gradient flow's bias in linear neural networks.
problem Understanding implicit bias in linear neural network training.
method Tensor formulation of neural networks, including fully-connected, diagonal, and convolutional networks.
result Gradient flow on linear tensor networks converges to solutions of specific optimization problems.
SGD converges to zero loss for separable data with fixed learning rate.
problem Optimizing homogeneous linear classifiers with SGD on linearly separable data.
method Proved convergence of SGD with fixed learning rate for separable data.
result SGD converges to zero loss for separable data with fixed learning rate.
This study investigates how gradient-based methods bias neural networks trained on high-dimensional data.
problem The implicit biases of gradient-based optimization algorithms in neural networks trained on high-dimensional data.
method Investigation of gradient flow and gradient descent in two-layer fully-connected neural networks with leaky ReLU activations.
result Gradient flow and gradient descent lead to neural networks with low-rank solutions and linear decision boundaries.
MMA training maximizes margins for adversarial robustness.
problem Adversarial robustness of neural networks.
method Directly maximizes margins through adaptive adversarial training.
result MMA training improves adversarial robustness compared to fixed ε adversarial training.
ARLD uses active deep Q-learning to learn faster with expert demonstrations.
problem Efforts required to obtain enough expert demonstrations for RL training.
method ARLD framework with Active Deep Q-Network (ADQN) for active demonstration queries.
result ARLD learns faster and reaches super-expert performance with expert demonstrations.
This paper simplifies deep learning networks by mapping them to a linear function of a feature map.
problem Understanding how weights in deep networks coordinate across layers and generalize.
method Reparameterizes DNNs as a linear function of a feature map, transforming depth-dependencies into tensor products.
result Develops sample compression representation of neural networks in terms of support vectors, showing sample complexity of O(ns/epsilon).
Unified approach for optimizing predictions in linear programming and inverse problems.
problem Optimizing predictions in linear programming and inverse problems.
method Maximum optimality margin approach.
result Unified approach that balances computational efficiency and theoretical properties.
We embed KKT points in neural networks of different sizes.
problem Classifying data using homogeneous neural networks.
method Introducing KKT point embedding principle and proving it for different network types.
result KKT points of a smaller network can be mapped to those of a larger network via linear transformations.
Metric learning is a key problem for many data mining and machine learning applications, and has long been dominated by Mahalanobis methods. Recent advances in nonlinear metric learning have demonstrated the potential power of non-Mahalanobis distance functions, particularly tree-based functions. We propose a novel non…