arXiv research

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

Efficient learning of minimax risk classifiers in high dimensions.

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

Paper presents adaptive minimax risk classifiers for multidimensional concept drift.

Paper develops MRCs for supervised classification using generalized maximum entropy.

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

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

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

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

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

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

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

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

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…

Study minimax linear regression under quantile risk, improving existing bounds and providing new results.

New method for multiclass classification reduces error bounds.

Study on estimating invertible functions with minimax analysis.

Paper improves risk bounds for nonconvex-strongly-concave minimax problems.

New estimator achieves minimax optimal risk in transfer learning.

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

The paper optimizes risk-sensitive RL with CVaR, achieving near-minimax-optimal results.

State-of-the-art adversarial attacks are aimed at neural network classifiers. By default, neural networks use gradient descent to minimize their loss function. The gradient of a classifier's loss function is used by gradient-based adversarial attacks to generate adversarially perturbed images. We pose the question whet…

We consider the binary classification problem in a setup that preserves the privacy of the original sample. We provide a privacy mechanism that is locally differentially private and then construct a classifier based on the private sample that is universally consistent in Euclidean spaces. Under stronger assumptions, we…

Develops estimators for near-optimal linear regression under distribution shift.

The paper establishes risk bounds for PU learning with label noise.

Paper explores generalization of minimax learners, proposing a new metric.

Sparse multinomial logistic regression for multiclass classification with feature selection.

Since its inception, the modus operandi of multi-task learning (MTL) has been to minimize the task-wise mean of the empirical risks. We introduce a generalized loss-compositional paradigm for MTL that includes a spectrum of formulations as a subfamily. One endpoint of this spectrum is minimax MTL: a new MTL formulation…

Study tests uniformity of categorical data against missing-ball alternatives, finding chi-squared test outperforms.

We consider random-design linear prediction and related questions on the lower tail of random matrices. It is known that, under boundedness constraints, the minimax risk is of order $d/n$ in dimension $d$ with $n$ samples. Here, we study the minimax expected excess risk over the full linear class, depending on the dist…

Develops high-probability minimax quantile bounds for statistical problems.

Deep neural network with l_1-regularization achieves nearly optimal risk bounds.

Local asymptotic minimax risk bounds in a locally asymptotically mixture of normal family of distributions have been investigated under asymmetric loss functions and the asymptotic distribution of the optimal estimator that attains the bound has been obtained.

Paper proposes ZO-SMD for MERO, achieving optimal convergence rates.

We present an information-theoretic framework for bounding the number of labeled samples needed to train a classifier in a parametric Bayesian setting. We derive bounds on the average $L_p$ distance between the learned classifier and the true maximum a posteriori classifier, which are well-established surrogates for th…

Study on kernel regression risk in high dimensions using Pinsker bound.

Here we propose a general theoretical method for analyzing the risk bound in the presence of adversaries. Specifically, we try to fit the adversarial learning problem into the minimax framework. We first show that the original adversarial learning problem can be reduced to a minimax statistical learning problem by intr…

Score attack method provides a lower bound on privacy-constrained minimax risk.

We consider the problem of binary classification with abstention in the relatively less studied \emph{bounded-rate} setting. We begin by obtaining a characterization of the Bayes optimal classifier for an arbitrary input-label distribution $P_{XY}$. Our result generalizes and provides an alternative proof for the resul…

Paper explores fair classification with bounded disparity using finite datasets.

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.

The paper explores the information-theoretic nature of excess risk in machine learning.

An algorithm learns from multiple models to match an oracle's risk.

Develops a robust learning method for unknown context distributions.

Paper analyzes minimax risks of personalized federated learning algorithms.

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…

In statistical inference problems, we wish to obtain lower bounds on the minimax risk, that is to bound the performance of any possible estimator. A standard technique to obtain risk lower bounds involves the use of Fano's inequality. In an information-theoretic setting, it is known that Fano's inequality typically doe…