New method computes discriminative classifiers from generative models.
problem Discriminative vs generative classifiers are often seen as distinct, but this work shows they can be equivalent.
method General theoretical result showing generative classifiers can be computed discriminatively.
result Bayesian Maximum Posterior classifier from generative models matches discriminative classifier definition.
Generative classifiers' properties are linked to linear constraints.
problem Understanding the Markov property in generative classifiers.
method Characterization of discrimination functions using linear constraints and a second order finite difference operator.
result Discrimination functions of undirected Markov network classifiers are characterized by sets of linear constraints.
Generative classifier derived from any discriminative classifier rejects illegal inputs.
problem Detecting and rejecting illegal inputs like adversarial examples and out-of-distribution samples.
method SDIM-logit: learns generative classifier from logits of any discriminative classifier, imposing statistical constraints.
result SDIM-logit inherits performance of base classifier without loss and can reject illegal inputs.
Generative text classifiers are most vulnerable to membership inference attacks.
problem Privacy threat from Membership Inference Attacks on generative text classifiers.
method Comprehensive empirical evaluation of generative, discriminative, and pseudo-generative classifiers across various datasets.
result Generative classifiers explicitly modeling P(X,Y) are most vulnerable to membership leakage. GWINs improve classifier accuracy by translating uncertain observations.
problem Improving accuracy of uncertain observations in classifiers.
method Generative network recovers correct observation distributions, reject option allows for uncertain predictions.
result GWINs significantly improve classifier accuracy on benchmark datasets.
This paper presents a novel kernel-based generative classifier which is defined in a distortion subspace using polynomial series expansion, named Kernel-Distortion (KD) classifier. An iterative kernel selection algorithm is developed to steadily improve classification performance by repeatedly removing and adding kerne…
New classifiers account for context-specific independences.
problem Restrictions in generative models for classification.
method Staged tree classifiers that account for context-specific independences.
result Staged tree classifiers achieve competitive classification accuracy.
Discriminative classifier for compositional data using hierarchical mixture of Generalized Dirichlet models.
problem Classifying compositional data, especially in spam detection and color space identification.
method Hierarchical mixture of discriminative Generalized Dirichlet classifiers, using variational approximation for parameter learning.
result First time a variational upper-bound for Generalized Dirichlet mixture is proposed in literature.
Study on the structure of classifier boundaries in DNA sequencing.
problem Understanding the structure of boundaries in a Bayes classifier for DNA sequencing.
method Examined the structure of the boundary in a Bayes classifier applied to DNA sequencing data. Introduced a new measure of uncertainty, Neighbor Similarity.
result The boundary is large and complex, and Neighbor Similarity effectively measures classifier uncertainty.
Random projections improve classifier generalization without needing to choose the best threshold.
problem Improving classifier generalization without choosing the best threshold.
method Thresholding a random one-dimensional feature after random projection of data.
result Generalization gap is significantly smaller than linear classifiers.
Random Hyperboxes is a simple yet effective ensemble classifier.
problem Improving classification accuracy using ensemble methods.
method Random subsets of sample and feature spaces are used to train individual hyperbox-based classifiers, which are then combined into an ensemble.
result The proposed classifier outperforms other fuzzy min-max neural networks and ensemble methods on 20 datasets.
Traditional classifiers can generate high-quality images comparable to generative models.
problem Separation between classifiers and generators in neural networks.
method Optimizing input gradients to produce images, using mask-based stochastic reconstruction, progressive-resolution technique, and distance metric loss.
result Traditional classifiers can generate high-fidelity images of 256imes256 resolution on ImageNet. FOCA method prevents co-adaptation between feature extractor and classifier.
problem Co-adaptation between feature extractor and classifier degrades neural network performance.
method FOCA method uses randomly-generated, weak classifiers to optimize feature extractor without explicit co-adaptation.
result FOCA features form a point-like distribution within the same class under special conditions.
There is a rising interest in studying the robustness of deep neural network classifiers against adversaries, with both advanced attack and defence techniques being actively developed. However, most recent work focuses on discriminative classifiers, which only model the conditional distribution of the labels given the …
Study explores cyberbullying datasets and classifier generalization.
problem Cyberbullying detection across different online communities.
method Analysis of various cyberbullying datasets and classifier generalization.
result Insight into classifier generalization power and interaction.
This paper studies the generalization error of invariant classifiers. In particular, we consider the common scenario where the classification task is invariant to certain transformations of the input, and that the classifier is constructed (or learned) to be invariant to these transformations. Our approach relies on fa…
PAC-Bayesian framework for fairness in stochastic and deterministic classifiers.
problem Theoretical guarantees on fairness for balancing predictive risk and fairness constraints.
method PAC-Bayesian framework for both stochastic and deterministic classifiers, covering a broad class of fairness measures.
result Derives generalization bounds for fairness, demonstrating tightness with empirical evaluation.
ManiGen generates adversarial examples without classifier knowledge.
problem Vulnerability of neural network classifiers to adversarial examples.
method Generates adversarial examples by searching along the manifold.
result Adversarial examples generated by ManiGen are as successful as state-of-the-art generators.
Paper analyzes mistake and generalization of MNIC classifiers.
problem Understanding the performance of interpolating classifiers.
method Elementary analyses of MNIC's regret and generalization.
result MNIC generalizes with a rate proportional to the norm of the interpolating solution and inversely proportional to the number of data points.
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.
Develops causal explanations for black-box classifiers.
problem Creating understandable explanations for complex models.
method Generative model with information-theoretic measures of causal influence.
result Learned latent factors influence classifier outputs.
New method uses off-the-shelf classifiers to improve diffusion generation without extra training.
problem Improving sample quality and controllability in conditional diffusion generation.
method Leveraging off-the-shelf classifiers in a training-free fashion with calibration and pre-conditioning techniques.
result Significant performance improvements (up to 20%) over existing guidance schemes.
Flexible classifier using Mahalanobis distances for non-elliptical distributions.
problem Classifying non-elliptical and multimodal distributions.
method Semiparametric classifier based on Mahalanobis distances and generalized additive models.
result The proposed classifiers outperform traditional methods in high-dimensional, low-sample-size scenarios.
Improves classification accuracy with noisy labels using generative classifiers.
problem Handling noisy labels in large-scale datasets.
method Robust Generative Classifier (RoG) on top of pre-trained DNNs.
result Significantly improves classification accuracy with no re-training of the deep model.
A bias classifier is introduced to resist adversarial attacks.
problem Resisting adversarial attacks on deep neural networks (DNNs).
method Introducing the bias part of a DNN with Relu as the activation function as a classifier, and adding a random first-degree part to make it information-theoretically safe.
result The bias classifier is more robust than DNNs of similar size against adversarial attacks.
We propose a novel technique to make neural network robust to adversarial examples using a generative adversarial network. We alternately train both classifier and generator networks. The generator network generates an adversarial perturbation that can easily fool the classifier network by using a gradient of each imag…
Several recent works have shown that state-of-the-art classifiers are vulnerable to worst-case (i.e., adversarial) perturbations of the datapoints. On the other hand, it has been empirically observed that these same classifiers are relatively robust to random noise. In this paper, we propose to study a \textit{semi-ran…
META-DES.H selects competent classifiers using meta-learning and dynamic weighting.
problem Selecting competent classifiers in dynamic ensemble selection.
method META-DES framework using meta-learning and dynamic weighting.
result Improvements in recognition accuracy on 30 datasets.
Generative GAN improves classifier performance with limited training data.
problem Limited training data for black-box API attacks.
method Generative adversarial network (GAN) to generate synthetic training data.
result Improves classifier performance with synthetic data.
New method controls classifier guidance in diffusion models.
problem Improving classifier guidance in diffusion models.
method Cross-entropy control of classifier gradients.
result Effective guidance vectors with mean squared error O(dε). 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.
Paper proposes a classifier to improve medical image classification with limited data.
problem Limited training data leads to overfitting in medical image classification.
method Uses reinforcement learning to update classifier parameters with generalization feedback from a subset of training data.
result Improves classification performance and demonstrates generalized learning.
The variational autoencoder (VAE) is a popular probabilistic generative model. However, one shortcoming of VAEs is that the latent variables cannot be discrete, which makes it difficult to generate data from different modes of a distribution. Here, we propose an extension of the VAE framework that incorporates a classi…
The paper introduces new Bayesian network classifiers for better classification accuracy.
problem Improving supervised classification accuracy using Bayesian network classifiers.
method Developed novel classes of generative classifiers based on staged tree models, extending Bayesian networks.
result Data-driven learning routines enhance the accuracy of the new classifiers.
Boosting improves accuracy by combining weak learners into a voting classifier.
problem Boosting's theoretical performance is sub-optimal, especially for voting classifiers.
method Proposes a randomized boosting algorithm that outputs voting classifiers with a single logarithmic dependency on sample size.
result Randomized boosting achieves a generalization error with a single logarithmic dependency on the sample size.
COOS-7 dataset benchmarks image classifier generalization.
problem Measuring generalization of image classifiers to out-of-sample datasets.
method Created COOS-7 dataset with varying covariate shifts; benchmarked multiple models.
result All classifiers failed to generalize to datasets with greater covariate shifts.
Generates confident out-of-distribution samples to improve classifier robustness.
problem Overconfidence in deep learning models on out-of-distribution inputs.
method Uses a GAN to generate out-of-distribution samples that the classifier is confident on, maximizing entropy.
result Shows effectiveness on handwritten characters and natural images datasets.
The paper proposes methods to predict classifier generalization with few labeled samples.
problem Measuring classifier generalization with limited labeled data.
method Analysis of generalization variability, transfer-based solutions in supervised, semi-supervised, and unsupervised settings.
result Simple measures correlate with classifier generalization and can predict it with confidence.
Naive Bayes can be used as a discriminative classifier, matching the definition of logistic regression.
problem The definition of generative and discriminative classifiers.
method Comparing Naive Bayes and logistic regression, showing they can be used in either generative or discriminative ways.
result Naive Bayes can be used as a discriminative classifier.
Improves multi-label classification with a new network model.
problem Improving multi-label classification accuracy.
method Introduces Classifier Chain Network (CCN) for multi-label classification.
result CCN outperforms benchmark methods in simulations and real data.
We propose a generic and interpretable learning framework for building robust text classification model that achieves accuracy comparable to full models under test-time budget constraints. Our approach learns a selector to identify words that are relevant to the prediction tasks and passes them to the classifier for pr…
Invariance to geometric transformations is a highly desirable property of automatic classifiers in many image recognition tasks. Nevertheless, it is unclear to which extent state-of-the-art classifiers are invariant to basic transformations such as rotations and translations. This is mainly due to the lack of general m…
Paper uses GANs to generate domains that evade DGA classifiers.
problem Evasion of DGA classifiers by generated domains.
method Optimized GAN variants to generate domains similar to benign ones.
result WGANGP variant of GAN is most effective at evading DGA classifiers.
The paper classifies invariant generalized complex structures on specific flag manifolds.
problem Classifying invariant generalized complex structures on partial flag manifolds.
method Proved that invariant generalized almost complex structures are constant in each component of the isotropy representation.
result All invariant generalized complex structures on partial flag manifolds with at most four isotropy summands are classified.
Distillation speeds up classifier training and provides insights into its success.
problem Empirical success of knowledge distillation without theoretical explanation.
method Study of linear and deep linear classifiers, proving a generalization bound.
result Three key factors for distillation success: data geometry, optimization bias, strong monotonicity.
CharBot generates unregistered domains not detected by DGA classifiers.
problem Detecting generated domain names in real-time.
method Simple, effective method producing unregistered domains not detected by state-of-the-art classifiers.
result Retraining classifiers on CharBot samples is not a viable defense strategy.
Generative model creates poisoning attacks against machine learning classifiers.
problem Poisoning attacks degrade machine learning classifier performance.
method Generative Adversarial Net with generator, discriminator, and classifier components.
result Effectively compromises machine learning classifiers, including deep networks.
New defense method for non-parametric classifiers robust against adversarial attacks.
problem Lack of robustness in non-parametric classifiers against adversarial attacks.
method Adversarial pruning method to preprocess datasets and a novel attack.
result Adversarial pruning provides a robust defense for non-parametric classifiers.