arXiv research

Minimax defense improves neural network security against gradient-based attacks.

Efficient learning of minimax risk classifiers in high dimensions.

Paper presents an efficient algorithm for learning minimax risk classifiers with large-scale data.

Recently, researchers have discovered that the state-of-the-art object classifiers can be fooled easily by small perturbations in the input unnoticeable to human eyes. It is also known that an attacker can generate strong adversarial examples if she knows the classifier parameters. Conversely, a defender can robustify …

Minimax solutions are weak solutions to Cauchy problems involving Hamilton--Jacobi equations, constructed from generating families quadratic at infinity of their geometric solutions. We give a complete description of minimax solutions and we classify their generic singularities of codimension not greater than 2.

MRCpy implements minimax risk classifiers with performance guarantees and distribution shift adaptability.

Paper presents adaptive minimax risk classifiers for multidimensional concept drift.

Develops a new minimax probability machine for imbalanced classification tasks.

Paper develops MRCs for supervised classification using generalized maximum entropy.

Study minimax rates for binary classifier estimation with margin conditions.

The paper analyzes kernel classifiers' performance in Sobolev spaces and proves their optimality.

Given a task of predicting $Y$ from $X$, a loss function $L$, and a set of probability distributions $Γ$ on $(X,Y)$, what is the optimal decision rule minimizing the worst-case expected loss over $Γ$? In this paper, we address this question by introducing a generalization of the principle of maximum entropy. Applying t…

A novel minimax classifier tackles imbalanced datasets with few minority samples.

Study on clustering in high dimensions with anisotropic Gaussian mixtures, showing interpolation can be optimal and robust.

We develop a worst-case analysis of aggregation of classifier ensembles for binary classification. The task of predicting to minimize error is formulated as a game played over a given set of unlabeled data (a transductive setting), where prior label information is encoded as constraints on the game. The minimax solutio…

Paper introduces MRCs that minimize worst-case 0-1 loss, providing tight performance guarantees.

We consider using an ensemble of binary classifiers for transductive prediction, when unlabeled test data are known in advance. We derive minimax optimal rules for confidence-rated prediction in this setting. By using PAC-Bayes analysis on these rules, we obtain data-dependent performance guarantees without distributio…

Study on DiTs' rates of approximation and estimation under various data assumptions.

The paper proves neural networks' consistency and optimal convergence rates for various function classes.

New method for multiclass classification reduces error bounds.

A new classifier uses Fermat distance for semi-supervised learning in high dimensions.

Proposes a deep neural network for multi-dimensional functional data classification.

Paper presents IMRCs for evolving tasks with forward and backward learning.

Paper tackles nonparametric classification with privacy constraints, achieving optimal accuracy.

Human learners have the natural ability to use knowledge gained in one setting for learning in a different but related setting. This ability to transfer knowledge from one task to another is essential for effective learning. In this paper, we study transfer learning in the context of nonparametric classification based …

This paper analyzes neural network classifiers' performance in binary classification.

Privacy-preserving binary classification using locally differential private data.

MRCs minimize worst-case expected 0-1 loss and provide performance guarantees.

Partial-monitoring games constitute a mathematical framework for sequential decision making problems with imperfect feedback: The learner repeatedly chooses an action, opponent responds with an outcome, and then the learner suffers a loss and receives a feedback signal, both of which are fixed functions of the action a…

Paper defends machine learning models from adversarial attacks using GLRT.

Paper develops robust $k$-NN algorithm for few samples.

Sparse multinomial logistic regression for multiclass classification with feature selection.

Paper explores fair classification with bounded disparity using finite datasets.

Proposes a fairness criterion for multi-objective optimization in classification.

We address the problem of aggregating an ensemble of predictors with known loss bounds in a semi-supervised binary classification setting, to minimize prediction loss incurred on the unlabeled data. We find the minimax optimal predictions for a very general class of loss functions including all convex and many non-conv…

We consider a standard binary classification problem. The performance of any binary classifier based on the training data is characterized by the excess risk. We study Bahadur's type exponential bounds on the minimax accuracy confidence function based on the excess risk. We study how this quantity depends on the comple…

DeepMPM uses MPM to make deep neural networks more robust against adversarial attacks.

Characterizes distribution-free rates in unbalanced classification problems.

Cascade classifiers are widely used in real-time object detection. Different from conventional classifiers that are designed for a low overall classification error rate, a classifier in each node of the cascade is required to achieve an extremely high detection rate and moderate false positive rate. Although there are …

Undersampling often outperforms other methods in nonparametric classification.

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…

A binary classifier capable of abstaining from making a label prediction has two goals in tension: minimizing errors, and avoiding abstaining unnecessarily often. In this work, we exactly characterize the best achievable tradeoff between these two goals in a general semi-supervised setting, given an ensemble of predict…

Developing classification methods with high accuracy that also avoid unfair treatment of different groups has become increasingly important for data-driven decision making in social applications. Many existing methods enforce fairness constraints on a selected classifier (e.g., logistic regression) by directly forming …

This research examines how the error rate of nearest neighbor classifiers varies with dataset size.

This paper addresses the problem of unsupervised domain adaption from theoretical and algorithmic perspectives. Existing domain adaptation theories naturally imply minimax optimization algorithms, which connect well with the domain adaptation methods based on adversarial learning. However, several disconnections still …

Two new algorithms solve nonconvex-strongly concave problems efficiently.

A novel decentralized algorithm improves minimax optimization in federated learning.

We investigate the use of Minimax distances to extract in a nonparametric way the features that capture the unknown underlying patterns and structures in the data. We develop a general-purpose and computationally efficient framework to employ Minimax distances with many machine learning methods that perform on numerica…