Predicting structured outputs can be computationally onerous due to the combinatorially large output spaces. In this paper, we focus on reducing the prediction time of a trained black-box structured classifier without losing accuracy. To do so, we train a speedup classifier that learns to mimic a black-box classifier u…
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
169,042 papers · 148 categories
Trend · papers per month
48 results for “classifier outputs”
A method for consensus prediction from probabilistic classifier outputs.
problem Combining probabilistic classifier outputs without prior information.
method Iteratively updating predictions based on classifier diversity and convergence.
result Consensus predictions converge to a decision based on classifier outputs' correspondence.
Boosting classifiers improve accuracy with noisy inputs.
problem Noisy communication or computation degrades boosting classifier accuracy.
method Optimize resource allocation for base classifiers based on importance metrics.
result Optimized noisy boosting classifiers are more robust than bagging.
Two strategies for training network classifiers with feature heterogeneity.
problem Training network classifiers with agents having varying feature sizes and unreliable local decisions.
method Promotes global and local smoothing of classifier outputs.
result Output smoothing makes network classifier dynamics more complex, requiring regularization of parameters.
In most classification tasks there are observations that are ambiguous and therefore difficult to correctly label. Set-valued classifiers output sets of plausible labels rather than a single label, thereby giving a more appropriate and informative treatment to the labeling of ambiguous instances. We introduce a framewo…
New approach detects out-of-distribution inputs without needing OOD samples.
problem Detecting incorrect classification of out-of-distribution inputs in deep neural networks.
method A one-class classifier trained on an early layer's output of the original classifier.
result Substantially better results compared to state-of-the-art approaches.
A new attack for probabilistic classifiers adapts to noise levels.
problem Adversarial examples can mislead probabilistic classifiers.
method Adapts HopSkipJump attack for probabilistic classifiers, adjusting queries based on noise levels.
result Decision-based attacks are effective against probabilistic classifiers, even with noise.
The paper explores the incompatibility between fair privacy, need-to-know, and fairness in classifier outputs.
problem The interaction between fair privacy, need-to-know, and fairness in classifier outputs.
method Formulated and explored the interaction between fair privacy, need-to-know, and fairness in classifier outputs.
result Optimal classifiers are generally incompatible with fair privacy and need-to-know.
Aggregates diverse zero-shot LLM outputs for better corporate disclosure classification.
problem Combining varied zero-shot LLM predictions for improved stock return prediction.
method Multi-prompt framework with three fixed zero-shot LLM classifiers, logistic meta-classifier aggregation.
result Aggregated model outperforms single classifiers and baseline models, increasing balanced accuracy from 0.566 to 0.606.
We provide a methodology, resilient feature engineering, for creating adversarially resilient classifiers. According to existing work, adversarial attacks identify weakly correlated or non-predictive features learned by the classifier during training and design the adversarial noise to utilize these features. Therefore…
SWD improves unsupervised domain adaptation by measuring classifier outputs.
problem Improving unsupervised domain adaptation between domains.
method Proposes sliced Wasserstein discrepancy (SWD) for feature distribution alignment.
result SWD effectively aligns source and target distributions for various tasks.
The study evaluates saliency metrics for image classifier outputs, finding inconsistencies and unreliability.
problem Inconsistencies and unreliability in saliency metrics for evaluating pixel relevance.
method Investigated existing saliency metrics, calculated and compared their consistency, and applied psychometric testing methods.
result Saliency metrics can be statistically unreliable and inconsistent, affecting comparative rankings.
A new approach to make classifiers safer by allowing them to abstain from making decisions on adversarial inputs.
problem Making machine learning systems robust against adversarial attacks, especially in safety-critical applications.
method Introducing a novel objective function and a simple baseline for adversarial robustness with abstention, followed by CARL (Combined Abstention Robustness Learning) for joint classifier and abstention region learning.
result Training with CARL results in a more accurate, robust, and efficient classifier than a simple baseline.
After being trained, classifiers must often operate on data that has been corrupted by noise. In this paper, we consider the impact of such noise on the features of binary classifiers. Inspired by tools for classifier robustness, we introduce the same classification probability (SCP) to measure the resulting distortion…
A CAE improves DNN's outlier and adversary defense.
problem Improving DNN's robustness against outliers and adversaries.
method Proposes a classification-autoencoder (CAE) that compresses samples into disjoint spaces and uses a decoder to classify and defend against adversaries.
result The CAE achieves state-of-the-art outlier recognition and near-lossless classification of adversaries.
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 …
A method for learning discontinuous functions using clustering, classification, and regression.
problem Supervised learning with highly nonlinear and discontinuous outputs.
method Three stages: clustering, classification, and separate regression for each class.
result Combining clustering, classification, and regression provides a robust and powerful approach.
Multi-output inference tasks, such as multi-label classification, have become increasingly important in recent years. A popular method for multi-label classification is classifier chains, in which the predictions of individual classifiers are cascaded along a chain, thus taking into account inter-label dependencies and…
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.
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.
Paper develops a probabilistic regressor chain method using Monte Carlo methods.
problem Improving multi-output regression with probabilistic chains.
method Develops a sequential Monte Carlo scheme for probabilistic regressor chains.
result Monte Carlo scheme for probabilistic regressor chains can be effective and useful.
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.
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.
Specialists outperform generalists in ensemble classification.
problem Determining the accuracy of an ensemble of classifiers when individual classifier accuracies are known.
method Proved upper and lower bounds on ensemble accuracy, constructed specialist and generalist classifiers.
result Upper and lower bounds on ensemble accuracy, practical implications for classifier construction.
ECNN combines binary classifiers to protect neural networks from adversarial attacks.
problem Vulnerability of neural networks to adversarial inputs.
method Designs an error-correcting code matrix to maximize row and column distances, training end-to-end.
result ECNN effectively defends against adversarial attacks with good accuracy on normal examples.
This paper provides new insight into maximizing F1 scores in the context of binary classification and also in the context of multilabel classification. The harmonic mean of precision and recall, F1 score is widely used to measure the success of a binary classifier when one class is rare. Micro average, macro average, a…
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.
Ensembles of classifier models typically deliver superior performance and can outperform single classifier models given a dataset and classification task at hand. However, the gain in performance comes together with the lack in comprehensibility, posing a challenge to understand how each model affects the classificatio…
Radiomics aims to extract and analyze large numbers of quantitative features from medical images and is highly promising in staging, diagnosing, and predicting outcomes of cancer treatments. Nevertheless, several challenges need to be addressed to construct an optimal radiomics predictive model. First, the predictive p…
Probabilistic classifiers output a probability distribution on target classes rather than just a class prediction. Besides providing a clear separation of prediction and decision making, the main advantage of probabilistic models is their ability to represent uncertainty about predictions. In safety-critical applicatio…
As deep learning methods form a critical part in commercially important applications such as autonomous driving and medical diagnostics, it is important to reliably detect out-of-distribution (OOD) inputs while employing these algorithms. In this work, we propose an OOD detection algorithm which comprises of an ensembl…
Deformable Classifiersstat.ML
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 …
Study on deep neural networks using concentration inequalities and optimal stopping.
problem Understanding the performance and structure of stochastic deep neural networks.
method Introduced concentration inequalities for SDNN outputs and an EC classifier. Determined the optimal number of layers via an optimal stopping procedure.
result Optimal number of layers for SDNNs determined via an optimal stopping procedure.
A new method calculates optimal decisions from classifier outputs, improving predictions in drug discovery.
problem Finding optimal decisions from classifier outputs in fields like medicine.
method Develops a transducer that calculates probabilities from classifier outputs, enabling expected-utility maximization.
result Improves prediction accuracy in drug discovery problems, sometimes close to theoretical maximum.
Method trains shared embedding to align inputs and outputs for domain adaptation.
problem Unsupervised domain adaptation between different data domains.
method Regularized conditional alignment objective function and adversarial regularization.
result Improves classifier performance on unseen domain.
We study the tradeoff between computational effort and classification accuracy in a cascade of deep neural networks. During inference, the user sets the acceptable accuracy degradation which then automatically determines confidence thresholds for the intermediate classifiers. As soon as the confidence threshold is met,…
Interprets neural network classifiers for categorical inputs.
problem Neural networks' interpretability in human-sensitive applications.
method Mapping to physical energy model, expansion of neural network layers.
result Each layer's contribution to classification can be analyzed.
This research discovers model architecture and training dataset characteristics through strategic input probing.
problem Discovering model architecture and training dataset characteristics in black box models.
method Structured input probes and model outputs are used to train a deep classifier for image and text classification.
result The approach successfully distinguishes between different image and text datasets and architectures.
Develops structured noise for more accurate graph classifier robustness certificates.
problem Isotropic noise limits robustness certificates for graph classifiers.
method Randomized smoothing with anisotropic noise distribution.
result Structured-aware robustness certificates provide more accurate predictions.
Neural networks exhibit simplex symmetry in their final and penultimate layers.
problem Understanding the symmetry in neural network layers.
method Analytical and numerical studies of toy models and deep neural networks.
result Neural networks map data points from the same class to a single point in a high-dimensional space, forming a simplex.
This paper improves deep learning model consistency through ensemble methods.
problem Consistency and correct-consistency issues in deep learning models.
method Formal definition of consistency and correct-consistency, proving ensemble improvement, proposing dynamic snapshot ensemble method.
result Ensemble methods can improve correct-consistency of deep learning models.
We revisit logistic regression and its nonlinear extensions, including multilayer feedforward neural networks, by showing that these classifiers can be viewed as converting input or higher-level features into Dempster-Shafer mass functions and aggregating them by Dempster's rule of combination. The probabilistic output…
Refinement revisited with connections to Bayes error, conditional entropy and calibrated classifiersstat.ML
The concept of refinement from probability elicitation is considered for proper scoring rules. Taking directions from the axioms of probability, refinement is further clarified using a Hilbert space interpretation and reformulated into the underlying data distribution setting where connections to maximal marginal diver…
CPR adds entropy maximization to improve continual learning methods.
problem Catastrophic forgetting in continual learning.
method Classifier-Projection Regularization (CPR) adds an entropy maximization term to existing regularization methods.
result CPR improves accuracy and plasticity in continual learning methods.
The original problem of supervised classification considers the task of automatically assigning objects to their respective classes on the basis of numerical measurements derived from these objects. Classifiers are the tools that implement the actual functional mapping from these measurements---also called features or …
Bayesian model fuses multiple classifiers with explicit correlation modeling.
problem Combining outputs of multiple classifiers with explicit correlation.
method Hierarchical Bayesian model with correlated Dirichlet distribution.
result Fused classifier performance can be Bayes optimal even for highly correlated base classifiers.
We introduce a novel approach for training adversarial models by replacing the discriminator score with a bi-modal Gaussian distribution over the real/fake indicator variables. In order to do this, we train the Gaussian classifier to match the target bi-modal distribution implicitly through meta-adversarial training. W…
We propose a new type of attack for finding adversarial examples for image classifiers. Our method exploits spanners, i.e. deep neural networks whose input space is low-dimensional and whose output range approximates the set of images of interest. Spanners may be generators of GANs or decoders of VAEs. The key idea in …