AdaBoost's classifier and margins converge to a known value.
problem Convergence properties of AdaBoost algorithm.
method Formal proofs of convergence properties of AdaBoost's classifier and margins.
result AdaBoost's classifier and margins converge to a known value.
New classifiers converge under large data, simplifying complex models.
problem Complex predictive models under large datasets.
method Convergence of simultaneous and marginal classifiers under partition exchangeability.
result Asymptotic convergence of classifiers with large data reduces computational complexity.
We study the rates of convergence from empirical surrogate risk minimizers to the Bayes optimal classifier. Specifically, we introduce the notion of \emph{consistency intensity} to characterize a surrogate loss function and exploit this notion to obtain the rate of convergence from an empirical surrogate risk minimizer…
Efficient poisoning attack converges to any target classifier with provable convergence.
problem Inducing a corrupted model that misbehaves in favor of an adversary.
method Online convex optimization to find poisoning points incrementally.
result Provably converges to any attainable target classifier.
A novel distributed adaptive NN classifier for large data sets.
problem Handling large and distributed data for efficient classification.
method Distributed adaptive nearest neighbor classifier with stochastic tuning parameter selection and early stopping rule.
result Achieves nearly optimal convergence rate under large sub-sample sizes.
This paper analyzes kNN convergence over feature transformations.
problem The curse of dimensionality affects kNN performance in transformed feature spaces.
method Developed a novel analysis on kNN convergence rates over transformed features, linking properties of the transformed space to raw feature space.
result Theoretical analysis explains why some feature transformations are better for kNN.
Convolutional neural networks improve image classification accuracy.
problem Improving accuracy in image classification.
method Analyzing the convergence rate of misclassification risk for image classifiers.
result A rate of convergence independent of image dimension proves the effectiveness of CNNs.
Deep neural networks outperform traditional methods in high-dimensional classification.
problem Understanding the empirical success of deep neural networks in high-dimensional classification.
method Proposed a teacher-student framework with Bayes classifier as ReLU neural networks, derived convergence rates for 0-1 and hinge losses.
result Sharp rate of convergence for classifiers trained using 0-1 or hinge loss, with Od(n−2/3) or Od(n−1) under separable data distribution. We study the implicit bias of gradient descent methods in solving a binary classification problem over a linearly separable dataset. The classifier is described by a nonlinear ReLU model and the objective function adopts the exponential loss function. We first characterize the landscape of the loss function and show th…
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.
We derive the fast convergence rates of a deep neural network (DNN) classifier with the rectified linear unit (ReLU) activation function learned using the hinge loss. We consider three cases for a true model: (1) a smooth decision boundary, (2) smooth conditional class probability, and (3) the margin condition (i.e., t…
Near-Exponential Convergence Rates for kNN Classification
problem Convergence rates for kNN classification
method Introducing Boltzmann margin
result First near-exponential convergence rates for kNN classification
Randomised classifiers outperform deterministic ones in strategic classification.
problem Strategic modification of features by agents in classification tasks.
method Theoretical analysis of randomised classifiers in strategic classification.
result Randomised classifiers can achieve better accuracy than deterministic ones under certain conditions.
The paper proves neural networks' consistency and optimal convergence rates for various function classes.
problem Proving neural networks' consistency and optimal convergence rates for diverse function classes.
method Analyzes wide and deep ReLU neural networks trained on logistic loss and Kolmogorov-Donoho optimal function classes.
result Proves universal consistency and minimax optimal convergence rates for neural networks.
This paper proposes a systematic framework to design a classification model that yields a classifier which optimizes a utility function based on prior knowledge. Specifically, as the data size grows, we prove that the produced classifier asymptotically converges to the optimal classifier, an extended version of the Bay…
Aimed at explaining the surprisingly good generalization behavior of overparameterized deep networks, recent works have developed a variety of generalization bounds for deep learning, all based on the fundamental learning-theoretic technique of uniform convergence. While it is well-known that many of these existing bou…
The stability of statistical analysis is an important indicator for reproducibility, which is one main principle of scientific method. It entails that similar statistical conclusions can be reached based on independent samples from the same underlying population. In this paper, we introduce a general measure of classif…
Adam optimizes linear classifiers with separable data.
problem Understanding Adam's implicit bias in linear logistic regression.
method Study of Adam's behavior on linearly separable data.
result Adam converges to a linear classifier with maximum ℓ∞-margin. DSI measures dataset separability for neural networks.
problem Difficulty in separating different classes of data in neural networks.
method Created the Distance-based Separability Index (DSI) to quantify dataset separability.
result DSI effectively measures dataset separability and indicates similar distributions of different classes.
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.
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.
Bayesian classifiers converge under certain exchangeability conditions with more data.
problem Predictive accuracy of marginal classifiers under varying data conditions.
method Introduced and compared mBpc and sBpc, provided computational scheme for PE sequences, and developed parameter estimation and testing methods.
result mBpc and sBpc converge under PE conditions with increasing data, validating mBpc's use.
In this paper, we study the problem of sparse multiple kernel learning (MKL), where the goal is to efficiently learn a combination of a fixed small number of kernels from a large pool that could lead to a kernel classifier with a small prediction error. We develop an efficient algorithm based on the greedy coordinate d…
New bounds show robust models can generalize well, contrary to prior theories.
problem Existing robustness-based error bounds are vacuous for the best classifier.
method Developed novel bounds that converge to the true error of the best classifier.
result New bounds converge to the true error of the best classifier, improving generalization.
We develop an algorithm for minimizing a function using n batched function value measurements at each of T rounds by using classifiers to identify a function's sublevel set. We show that sufficiently accurate classifiers can achieve linear convergence rates, and show that the convergence rate is tied to the difficu…
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.
A new classifier uses linear programming to classify sets based on their covariance.
problem Classifying sets of observations as a whole, not individually.
method Proposes a new classifier, CLIPS, using linear programming for set classification.
result The CLIPS classifier performs better with multiple observations in a set.
Adversarial training is a principled approach for training robust neural networks. Despite of tremendous successes in practice, its theoretical properties still remain largely unexplored. In this paper, we provide new theoretical insights of gradient descent based adversarial training by studying its computational prop…
We introduce a variant of the k-nearest neighbor classifier in which k is chosen adaptively for each query, rather than supplied as a parameter. The choice of k depends on properties of each neighborhood, and therefore may significantly vary between different points. (For example, the algorithm will use larger $k…
The paper classifies flows of ancient curves in 2D space.
problem Classifying closed convex flows by curvature powers.
method Sub-affine-critical powers of curvature for flow classification.
result Ancient flows converge exponentially to smooth shrinkers.
Convolutional neural networks converge quickly with gradient descent.
problem Learning efficient image classifiers with over-parameterized networks.
method Gradient descent for training over-parametrized CNNs with global average-pooling.
result Gradient descent quickly reduces the misclassification risk of CNNs.
Develops fair classifiers robust to training distribution perturbations.
problem Ensuring fairness in classifiers robust to training data perturbations.
method Formulates a min-max objective function to minimize distributionally robust training loss while maintaining fairness for perturbed distributions. Uses an iterative online learning algorithm to find a fair and robust classifier.
result Our classifier maintains fairness and accuracy for a wide range of perturbations compared to state-of-the-art fair classifiers.
Several numerical approximation strategies for the expectation-propagation algorithm are studied in the context of large-scale learning: the Laplace method, a faster variant of it, Gaussian quadrature, and a deterministic version of variational sampling (i.e., combining quadrature with variational approximation). Exper…
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.
New image classifier uses hierarchical max-pooling with local pooling.
problem Improving image classification accuracy with variable spatial relationships.
method Introduces a hierarchical max-pooling model with additional local pooling for convolutional neural networks.
result Demonstrates improved performance in estimating image features.
This study examines when non-parametric methods are robust to adversarial examples.
problem Understanding when non-parametric methods are robust to adversarial examples.
method Examined general non-parametric methods and established conditions for r-consistency.
result Non-parametric methods like nearest neighbors and kernel classifiers are r-consistent when data is well-separated, while histograms are not.
Gradient descent is a simple and widely used optimization method for machine learning. For homogeneous linear classifiers applied to separable data, gradient descent has been shown to converge to the maximal margin (or equivalently, the minimal norm) solution for various smooth loss functions. The previous theory does …
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. When randomized ensembles such as bagging or random forests are used for binary classification, the prediction error of the ensemble tends to decrease and stabilize as the number of classifiers increases. However, the precise relationship between prediction error and ensemble size is unknown in practice. In the standar…
Mirror flow optimizes separable data problems, converging to a maximum margin classifier.
problem Optimizing classification problems with separable data using mirror flow.
method Examine mirror flow on linearly separable classification problems, focusing on the horizon function of the mirror potential.
result Mirror flow converges to a maximum margin classifier for separable data under certain conditions.
Detects changes in classifier scores to identify shifts in class priors.
problem Label shift changes in classification data.
method Sequential changepoint detection of classifier scores.
result Outperforms other detection procedures in label shift settings.
This belongs to a series of papers devoted to the study of the cohomology of classifying spaces of Lie groupoids. Our aim here is to introduce and study the notion of representation up to homotopy of Lie groupoids, the resulting derived category, and to show that the adjoint representation is well defined as a represen…
Study on hyperbolic elastic flow, proving convergence and quantifying singularities.
problem Understanding singularities and convergence of elastic flow in hyperbolic plane.
method Analyzes closed and open curves with clamped boundary conditions, proving convergence without small energy assumption.
result Each singularity carries an energy cost of at least 8, and blow-ups are explicitly classified.
FA algorithm provides convergence guarantees for deep linear networks.
problem Training efficiency and convergence of deep neural networks.
method Theoretical analysis of Feedback Alignment (FA) algorithm for deep linear networks.
result Certain initializations lead to implicit anti-regularization, affecting learning effectiveness.
Active learning is an important technique to reduce the number of labeled examples in supervised learning. Active learning for binary classification has been well addressed in machine learning. However, active learning of the reject option classifier remains unaddressed. In this paper, we propose novel algorithms for a…
We study the effect of imperfect training data labels on the performance of classification methods. In a general setting, where the probability that an observation in the training dataset is mislabelled may depend on both the feature vector and the true label, we bound the excess risk of an arbitrary classifier trained…
Paper improves classification rates for private data.
problem Classifying data with privacy constraints and relaxed assumptions.
method Introduced a novel approach for classification under privacy constraints, relaxing the strong density assumption.
result Achieved minimax optimal convergence rates without strong density assumption.
Approach collects missing outcomes to improve fairness in classification.
problem Lack of true outcomes for incorrectly classified samples leads to biased classifiers.
method Exploration-based data collection to ensure all subpopulations are represented and fairness properties are encoded.
result Trained classifier converges to a fair classifier with bounded false positives.