Paper compares two multi-label classification methods: Bayes metaclassifier and soft-confusion-matrix.
problem Comparing multi-label classification methods under the same framework.
method Bayes metaclassifier combined with problem-transformation approach, and soft-confusion-matrix classifier.
result Both methods perform similarly, but statistical analysis provides insights.
A theoretical study is presented for a simple linear classifier called reference distance estimator (RDE), which assigns the weight of each feature j as P(r|j)-P(r), where r is a reference feature relevant to the target class y. The analysis shows that if r performs better than random guess in predicting y and is condi…
Denoised smoothing defends pretrained classifiers against adversarial attacks.
problem Adversarial attacks on pretrained classifiers.
method Prepending a denoiser to any off-the-shelf classifier using randomized smoothing.
result Guaranteed ℓp-robustness to adversarial examples without modifying the pretrained classifier. Paper proposes using truncated normal distribution for RRC model, improving detection of minority classes.
problem Improving weak classifiers in RRC models.
method Proposes using truncated normal distribution and soft confusion matrix for RRC model.
result Truncated-normal-based SCM algorithm outperforms beta distribution in discovering minority classes.
Improved neural network robustness to adversarial attacks through smoothed inference.
problem Vulnerability of deep neural networks to adversarial attacks.
method Randomized smoothing applied to adversarial training, improving both robustness and performance.
result Significant improvement in accuracy on adversarial attacks (e.g., 60.4% on CIFAR-10 with ResNet-20, outperforming previous methods by 11.7%).
Time series classification has received great attention over the past decade with a wide range of methods focusing on predictive performance by exploiting various types of temporal features. Nonetheless, little emphasis has been placed on interpretability and explainability. In this paper, we formulate the novel proble…
Complex systems are typically represented by large ensembles of observations. Correlation matrices provide an efficient formal framework to extract information from such multivariate ensembles and identify in a quantifiable way patterns of activity that are reproducible with statistically significant frequency compared…
Research proposes classifiers to distinguish tweets with conflicting cashtags.
problem Cryptocurrency cashtags interfere with stock company cashtags on Twitter.
method Heuristic and supervised classifiers analyzed for distinguishing tweets.
result Independent Models perform best in distinguishing tweets with conflicting cashtags.
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.
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.
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…
This study compares feature importance and explainability in quantum vs classical ML models.
problem Lack of transparency in ML models, especially in sensitive fields.
method Comparison of classical ML (SVM, Random Forest) and hybrid quantum ML (VQC, QSVC) models using feature importance and explainability methods.
result Quantum ML models provide insights similar to classical models but with unique quantum features.
The paper verifies the robustness of classifier ensembles against randomized attacks.
problem Ensuring classifier ensembles are robust against arbitrary randomized attacks.
method Formal verification procedure using SMT and MILP encodings to assess robustness.
result Proves the NP-hardness of the robustness-checking problem and provides upper bounds on attack sets.
Rule-based classifiers quantify uncertainty using Bernoulli random variables.
problem Quantifying the uncertainty of precision estimates for rule-based text classifiers.
method Treat partitions of sub-strings as Bernoulli random variables, compare means using statistical tests, and combine classifiers using Dempster-Shafer theory.
result The approach can be used to combine binary classifiers into a multi-label classifier.
RS-Del provides robustness for sequence classifiers against edit distance attacks.
problem Certifying robustness of discrete sequence classifiers against edit distance attacks.
method Randomized deletion (RS-Del) for discrete sequence classifiers, focusing on edit distance-bounded adversaries.
result Achieved a certified accuracy of 91% at an edit distance radius of 128 bytes on malware detection.
Randomized classifiers outperform deterministic ones in robustness against adversarial attacks.
problem Ensuring optimal robustness against all adversarial attacks.
method Game-theoretic approach, focusing on the non-existence of Nash equilibrium in deterministic classifiers and demonstrating the superiority of randomized classifiers.
result Randomized classifiers can outperform deterministic ones in robustness against adversarial attacks.
Estimates missing data points in classifier inputs based on training data.
problem Estimating the proportion of unseen data points in classifier inputs.
method Characterizes the expected missing mass in terms of the sample and uses optimization to find nearly unbiased estimators with minimized MSE.
result Found estimators with MSE roughly 80% of the Good-Turing estimator's, improving over 93% of runs.
Improved scalability of BOSS ensemble for time series classification.
problem Non-trivial scalability issues in BOSS and WEASEL.
method Random selection of classifiers, ensembling techniques, and build time reduction.
result Significant reduction in build time with minimal accuracy loss.
Geometric variations of objects, which do not modify the object class, pose a major challenge for object recognition. These variations could be rigid as well as non-rigid transformations. In this paper, we design a framework for training deformable classifiers, where latent transformation variables are introduced, and …
New methods for ordinal classification of interval-valued data and functional data.
problem Ordinal classification of interval-valued data and functional data.
method Six ordinal classifiers are proposed, including parametric, binary decomposition, logistic regression, distance-based, k-nearest-neighbor, kernel PCA, and random forest methods.
result Considering ordering and interval-valued information improves the accuracy of ordinal classification.
Consider a binary decision making process where a single machine learning classifier replaces a multitude of humans. We raise questions about the resulting loss of diversity in the decision making process. We study the potential benefits of using random classifier ensembles instead of a single classifier in the context…
Randomized classifiers improve strategic classification efficiency.
problem Designing optimal classifiers in strategic classification games.
method Investigation of randomized classifiers and their efficiency in strategic classification.
result Randomized classifiers are necessary for maximizing classification efficiency.
Reservoir Computing (RC) refers to a Recurrent Neural Networks (RNNs) framework, frequently used for sequence learning and time series prediction. The RC system consists of a random fixed-weight RNN (the input-hidden reservoir layer) and a classifier (the hidden-output readout layer). Here we focus on the sequence lear…
Study improves image classifier robustness to random p-norm corruptions.
problem Improving robustness of image classifiers to real-world imperceptible corruptions.
method Training and testing with random p-norm corruptions, evaluating robustness against different p-norms.
result Training with a combination of p-norm corruptions significantly improves robustness.
Attention forcing improves sequence-to-sequence model training stability.
problem Training auto-regressive sequence-to-sequence models with attention mechanism is challenging.
method Attention forcing guides the model with generated output history and reference attention.
result Attention forcing trains models to recover from mistakes without requiring a schedule or classifier.
Unhinged loss minimization fails to improve classifier accuracy for simple data.
problem Accuracy of classifiers minimizing the unhinged loss.
method Minimizing the unhinged loss function.
result Minimizing the unhinged loss yields classifiers with accuracy no better than random guessing for simple data.
The paper bounds solutions to complex optimization problems with uncertain data.
problem Distributionally robust optimization problems with multivariate uncertainty sets.
method Conditions and bounds derived for multivariate and univariate Wasserstein distances, Bregman-Wasserstein divergences, and signed Choquet integrals.
result Computable lower and upper bounds for DRO problems, derived from scalar-valued aggregation functions and Wasserstein distances.
We study the theoretical properties of learning a dictionary from N signals xi∈RK for i=1,...,N via l1-minimization. We assume that xi's are i.i.d. random linear combinations of the K columns from a complete (i.e., square and invertible) reference dictionary $\mathbf D_0 \in…
Paper introduces metrics to detect unintended bias in text classifiers.
problem Unintended bias in machine learning classifiers.
method Threshold-agnostic metrics considering various score distribution variations across groups.
result New metrics reveal subtle unintended bias in public models.
Random forests classify Pokemon names based on evolutionary status.
problem Classifying Pokemon names into pre-evolution and post-evolution categories.
method Trained random forests using sound symbolism from Pokemon names, conducted experiments with human participants.
result Random forests outperform human participants in classifying Pokemon names.
Random Gaussian noise and pixel discretization improve image classifier robustness.
problem Whitebox adversarial attacks decrease classifier accuracy.
method Inject random Gaussian noise, discretize pixels, and use any classifier.
result Reduces KL divergence and lower bound on classifier accuracy.
VORACE uses random classifiers to vote for the best class, saving time and expertise.
problem Finding the best classifier for a dataset is costly and requires domain expertise.
method Randomly generated classifiers vote to determine the best class ranking.
result VORACE outperforms state-of-the-art methods on various datasets.
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.
New method defends machine learning models from black-box attacks.
problem Protecting machine learning models from black-box transfer attacks.
method Randomized ensemble technique with provable security guarantee.
result Empirical evidence of security for random binary classifiers.
There is a large literature explaining why AdaBoost is a successful classifier. The literature on AdaBoost focuses on classifier margins and boosting's interpretation as the optimization of an exponential likelihood function. These existing explanations, however, have been pointed out to be incomplete. A random forest …
DAMVI algorithm improves imbalanced binary classification by adjusting weights of examples and classifiers.
problem Imbalanced binary classification tasks where minority class is underrepresented.
method DAMVI algorithm increases positive example weights and optimizes classifier weights using PAC-Bayesian C-Bound.
result DAMVI outperforms state-of-the-art models on various imbalanced datasets.
The Minimal Learning Machine improves regression performance with reference point selection.
problem Improving the performance of the Minimal Learning Machine (MLM) in regression tasks.
method Developed theoretical guarantees for MLM's interpolation and approximation capabilities. Proposed clustering-based methods for selecting reference points to enhance MLM's generalization.
result Clustering-based methods for reference point selection outperform random selection, especially with a small number of points.
Enhances robustness of deep neural networks with randomized smoothing.
problem Improving robustness of deep neural networks against noisy inputs and adversarial attacks.
method Introduces a variance-margin trade-off approach to increase certified robust radius using pre-trained models.
result Significant improvement in certified accuracy compared to state-of-the-art methods.
ELECTRE Tree infers ELECTRE Tri-B parameters using a machine learning approach.
problem Infer ELECTRE Tri-B parameters from decision-maker inputs.
method Random Forest inspired algorithm: generate models, optimize parameters, merge or vote.
result ELECTRE Tree generates non-linear decision boundaries for voting, linear for merged model.
Advances adversarial training of smoothed classifiers for robust deep learning.
problem Building neural network classifiers robust to adversarial attacks.
method Adversarial training of randomized smoothed classifiers with an adapted attack.
result Significantly outperforms existing provably robust classifiers on ImageNet and CIFAR-10.
Certified robustness for ImageNet models with randomized smoothing.
problem Creating robust models against adversarial attacks.
method Randomized smoothing with Gaussian noise.
result Certified top-1 accuracy of 49% on ImageNet under small ℓ2 perturbations. Improved local feature attributions using neighbourhood reference distributions.
problem Misleading results from global population in local model behaviour.
method Formulation of neighbourhood reference distributions and self-normalised importance sampling.
result Neighbourhood Shapley values provide meaningful sparse feature attributions.
This paper evaluates defenses against adversarial attacks on neural networks.
problem Adversarial attacks can trick DNNs into mis-classifying inputs.
method Scientific evaluation methodology for randomized defenses.
result RPENNs outperformed other defenses against adversarial attacks.
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.
A new method detects changes in multivariate data using random forests.
problem Detecting changes in multivariate data.
method A computationally feasible search method using random forests and class probability predictions.
result Consistently locates change points in simulations.
Classifies 3D manifolds with specific structures and automorphisms.
problem Classifying compact 3D manifolds with path structures and large automorphism groups.
method Uses Cartan connections and constant curvature analysis.
result Curvature of Cartan connections is constant for these manifolds.
Calibrating classifiers reduces grouping loss using sufficiency criteria.
problem Grouping loss in probabilistic classifier calibration is often overlooked.
method Revisited Langford & Zadrozny's probing reduction approach and introduced Brier curves.
result The probing reduction approach reduces grouping loss and supports sufficient calibration.
We study the performance of data-driven, a priori and random approaches to label space partitioning for multi-label classification with a Gaussian Naive Bayes classifier. Experiments were performed on 12 benchmark data sets and evaluated on 5 established measures of classification quality: micro and macro averaged F1 s…