Study controls error rates of binary classifiers using hypothesis testing.
problem Traditional binary classifiers have uncontrolled error rates.
method Combines binary classification with statistical hypothesis testing.
result Trained classifiers can be made to meet target error rate thresholds.
Optimizes binary rating systems for item ranking.
problem Designing efficient feedback systems for item ranking.
method Formalizes performance, provides algorithm, empirically designs and validates.
result Empirically designed and validated approximately optimal rating system.
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 ) \mathcal{O}(n^{-1}) O ( n − 1 ) for different function classes. Paper bounds convergence rate of adversarial surrogate risk.
problem Vulnerability of binary classification models to adversarial attacks.
method Characterizes conditions for adversarial consistency and provides surrogate risk bounds.
result Surrogate risk bounds quantify the rate of convergence of adversarial classification risk.
New method reduces unfairness in binary classification.
problem Achieving similar false positive and negative rates across two populations.
method Penalizes unfairness to achieve balanced false positive and negative rates.
result Empirically validated approach improves fairness and accuracy.
This paper studies universal rates of ERM for binary classification under agnostic learning.
problem The challenge of achieving universal rates of ERM for binary classification under agnostic learning.
method The paper explores the agnostic universal rates of ERM for binary classification, revealing three possible rates: e − n e^{-n} e − n , o ( n − 1 / 2 ) o(n^{-1/2}) o ( n − 1/2 ) , or arbitrarily slow. result The paper provides a complete characterization of which concept classes fall into each of the three categories of agnostic universal rates.
Privacy-preserving binary classification using locally differential private data.
problem Classifying data while protecting individual privacy.
method Locally differential private mechanism followed by a universally consistent classifier.
result Minimax rates of convergence are slower when using private data.
Theory extends optimal learning rates without realizability assumption.
problem Agnostic binary classification without realizability assumption.
method Identifies tetrachotomy of optimal rates and combinatorial structures.
result Optimal universal rates for binary classification in agnostic setting.
A method for making predictions with a reject option using conformal prediction.
problem Uncertainty in machine learning predictions, especially when models are unsure.
method Formalizing ML with reject option, using conformal prediction for distribution-free error guarantees.
result Theoretical guarantees on error rate for prediction sets with distribution-free validity.
Paper estimates FPR of Bayes classifier using soft labels.
problem Determining optimal classifier performance.
method Uses soft labels and denoising technique.
result Consistent and unbiased FPR estimator developed.
This paper shows faster convergence rates for stochastic gradient descent in binary classification.
problem Achieving faster convergence rates for stochastic gradient descent in binary classification.
method Stochastic gradient descent and averaging variant, focusing on exponential convergence rates under strong low-noise conditions.
result Exponential convergence of the expected classification error in the final phase of stochastic gradient descent and averaged stochastic gradient descent for differentiable convex loss functions.
The multi-layer IB problem optimizes relevance and compression rates.
problem Optimizing relevance and compression rates in multi-layer information propagation.
method Single-letter characterization of the rate-relevance region, conditions for successive refinability, and counterexamples.
result Successive refinability of binary and Gaussian models, counterexample provided.
Paper analyzes learning rates for SVM with Gaussian kernels.
problem Optimizing learning rates for binary classification.
method Refined error analysis for SVM with Gaussian kernel and convex loss.
result SVM with Gaussian kernel can achieve optimal learning rates under certain conditions.
New online learning algorithm combines PA and TER for binary classification.
problem Binary classification with non-separable data and data imbalance.
method Online Passive-Aggressive (PA) and Total-Error-Rate (TER) learning combined into PATER algorithm.
result PATER algorithms outperform existing online learning algorithms in efficiency and effectiveness.
In statistical learning theory, convex surrogates of the 0-1 loss are highly preferred because of the computational and theoretical virtues that convexity brings in. This is of more importance if we consider smooth surrogates as witnessed by the fact that the smoothness is further beneficial both computationally- by at…
New optimization method improves AUC for binary classification and changepoint detection.
problem Non-convex AUC and sub-optimal points in ROC curves.
method AUM (Area Under Min(FP, FN)) surrogate loss function based on sorting and summing ROC curve points.
result AUM minimization learning algorithm improves AUC and speeds up compared to previous methods.
Binary funding impacts simplify derivative pricing models.
problem Complexity in derivative pricing due to varying lending/borrowing rates.
method Analyzes the binary nature of funding impacts leading to linear or semi-linear equations.
result Derivatives pricing simplifies when only one rate affects the payoff function.
In this article, we study the problem of pricing defaultable bond with discrete default intensity and barrier under constant risk free short rate using higher order binary options and their integrals. In our credit risk model, the risk free short rate is a constant and the default event occurs in an expected manner whe…
Proposes a classifier with bounded abstention rate for binary classification.
problem Binary classification with abstention rate constraints.
method Characterizes Bayes optimal classifier, proposes plug-in classifier with abstention region, and develops computationally efficient algorithm.
result Proposed classifier achieves high probability of satisfying abstention constraint and is minimax near-optimal.
Proposes a novel SVM model for binary classification with different misclassification costs.
problem Real-world classification problems with varying misclassification costs.
method Incorporates performance constraints in SVM formulation to seek a hyperplane with maximal margin and misclassification rates below given thresholds.
result The proposed model gives users control over misclassification rates in one class at the expense of the other.
We prove new fast learning rates for the one-vs-all multiclass plug-in classifiers trained either from exponentially strongly mixing data or from data generated by a converging drifting distribution. These are two typical scenarios where training data are not iid. The learning rates are obtained under a multiclass vers…
Paper discusses binary classification with metric space predictors, privacy constraints, and convergence rates.
problem Binary classification with metric space predictors under privacy constraints.
method Derives convergence rates for Proto-NN classifier with and without privacy constraints.
result Proto-NN classifier is universally consistent under privacy constraints.
Proposes MRIV framework for unbiased CATE estimation using binary IVs.
problem Bias in estimating CATEs due to unobserved confounders.
method Multiply robust machine learning framework (MRIV) for binary IVs.
result MRIV yields multiple robust convergence rates and outperforms existing methods.
Proposes GBBHE for efficient large-scale regression.
problem Large-scale regression problems.
method Gradient Boosting with binary histogram partition and ensemble learning.
result Improves computational efficiency and performance on large datasets.
BET improves nonparametric dependence detection by avoiding power loss.
problem Power loss in nonparametric dependence detection methods.
method Binary expansion statistics (BEStat) and binary expansion testing (BET) framework.
result BET avoids non-uniform consistency and achieves the minimax rate in sample size requirement.
Study on CNNs' learning rates and approximation capacities.
problem Learning rates and approximation capacities of CNNs.
method New approximation bound and covering number analysis for CNNs.
result Derives minimax optimal convergence rates for CNNs in various learning problems.
The paper develops bounds for predictive values in binary classification.
problem Lack of confidence intervals for positive and negative predictive values.
method Bi-criterion framework and distribution-free large deviation and uniform convergence bounds.
result New bounds for predictive values without relying on concentration inequalities.
Deep learning optimizes polar codes for better performance.
problem Designing efficient polar codes for error correction.
method Representing polar code indices as neural network weights, optimizing through gradient descent.
result Significant performance improvements over existing methods.
Crowdsourcing is an effective tool for human-powered computation on many tasks challenging for computers. In this paper, we provide finite-sample exponential bounds on the error rate (in probability and in expectation) of hyperplane binary labeling rules under the Dawid-Skene crowdsourcing model. The bounds can be appl…
This paper analyzes neural network classifiers' performance in binary classification.
problem Performance of neural network classifiers in binary classification problems.
method Plug-in classifiers based on neural networks, considering a more general function class and surrogate loss.
result Dimension-free, uniform rate of convergence for the excess risk of neural networks, showing minimax optimality.
Flexible framework for transfer learning with optimal rates.
problem Inference about a target population using related source data.
method Adaptive transfer learning framework allowing covariate-dependent relationships.
result Achieves minimax optimal rates of convergence by adapting to transfer relationship.
Extends BBSM model to incorporate ESG ratings and path dynamics.
problem Price stock options considering historical market index dynamics and ESG ratings.
method Develops discrete, binary tree option pricing model under BBSM with ESG valuation.
result Model accurately fits stock price changes and European call option prices.
New algorithm optimizes AUC in binary classification and changepoint detection.
problem Difficult to optimize AUC in binary classification and changepoint detection.
method Proposes efficient path-following algorithms for choosing optimal learning rate.
result Proposed line search algorithm computes complete AUM/AUC representation.
A new meta-learning method for faster adaptive multiclass classification.
problem Efficiently designing multiclass classifiers that adaptively merge classes into a hierarchical structure.
method Adaptive hierarchical classification tree construction using empirical Bayes error rates and minimal spanning trees.
result The proposed method can learn faster and achieve competitive accuracy compared to existing methods.
LxCIM metric improves binary classification performance evaluation.
problem Evaluation metrics for binary classification are often not invariant to local class exchange.
method Proposes LxCIM, a rank-based metric invariant to local class exchange.
result LxCIM addresses limitations of existing metrics like AUROC.
New exact tests detect changepoints in binary and count data, especially when normal approximations fail.
problem Detecting changepoints in multichannel binary and count data.
method Exact tests combining two-sample conditional tests with multiplicity correction.
result Exact tests are much more powerful than asymptotic tests in various settings.
For the problem of binary linear classification and feature selection, we propose algorithmic approaches to classifier design based on the generalized approximate message passing (GAMP) algorithm, recently proposed in the context of compressive sensing. We are particularly motivated by problems where the number of feat…
We investigate the effect of tax evasion on the income distribution and the inequality index of a society through a kinetic model described by a set of nonlinear ordinary differential equations. The model allows to compute the global outcome of binary and multiple microscopic interactions between individuals. When evas…
Optimizes clustering from noisy binary feedback in crowdsourcing.
problem Clustering items from binary user feedback with noisy answers.
method Develops algorithms for clustering items using adaptive selection of questions and items.
result Adaptive algorithm achieves performance close to information-theoretical limits.
We tackle binary tensor decomposition with a multilinear model and likelihood-based estimation.
problem Decomposing binary tensors with probabilistic models.
method Multilinear Bernoulli model, rank-constrained likelihood estimation, alternating optimization.
result The estimation error bound is established and shown to be minimax optimal.
Reinforcement learning improves wireless systems' rate adaptation.
problem Optimizing rate adaptation in 4G/5G systems using ACK/NACK feedback.
method Formulated as a Multi-Armed Bandit problem, proposed binary search algorithm with PAC guarantees.
result Achieved PAC solution for OLLA with binary search, outperforming UCB methods.
Batch normalization biases linear models towards uniform margins, improving performance in binary classification.
problem Understanding the implicit bias of batch normalization in linear models and neural networks.
method Analyzing gradient descent convergence on linear models and two-layer CNNs with batch normalization.
result Gradient descent with batch normalization in linear models converges to a uniform margin classifier with an exponential convergence rate.
Researchers prove inner product recovery is impossible in latent space models.
problem Recovering inner products in latent space models with random geometric graphs.
method Rate-distortion theory applied to Gaussian or spherical latent locations.
result Impossible to recover inner products if dimensionality exceeds n h ( p ) n h(p) nh ( p ) , matching positive results' conditions. Linearized probit regression matches nonlinear methods in accuracy.
problem Binary regression accuracy with nonlinear methods.
method Linearizing probit model with linear estimators.
result Linearized estimators perform similarly to nonlinear methods.
Binary feedback outperforms ordinal comparisons in ranking recovery.
problem Challenges the conventional wisdom that ordinal comparisons offer richer information.
method Proposes a parametric framework for modeling ordinal paired comparisons, binarizing ordinal data, and proving faster convergence rates for binary comparisons.
result Binarizing ordinal data significantly improves ranking recovery accuracy and exhibits a substantial performance gap.
Proposes an efficient algorithm for identifying important features in binary classification.
problem Understanding explainability of deep neural networks in binary classification.
method Variable-importance framework combined with lazy training.
result Achieves well-controlled error rates with minimal assumptions.
New method estimates hidden binary mixture model centers efficiently.
problem Estimating centers in high-dimensional binary mixture models with hidden Markov structure.
method Proposes a minimax optimal procedure and an adaptive variant.
result Achieves optimal rate of order δ d / n + d / n \sqrt{δd/n} + d/n δ d / n + d / n . Estimates individualized thresholds for binary responses using high-dimensional data.
problem Estimating individualized thresholds in high-dimensional settings with binary responses.
method Proposes an empirical risk minimization approach based on a regularized smoothed loss function to handle computational and theoretical challenges.
result Shows nonstandard asymptotic error bound and minimax rate optimality for estimating the high-dimensional parameter.