The paper develops a new algorithm for constructing minimax estimators using online learning techniques.
problem Designing minimax estimators for probability distribution parameters.
method Viewing the problem as a zero-sum game and using online learning with non-convex losses to find a Nash equilibrium.
result The algorithm constructs both a minimax estimator and a least favorable prior.
Many tasks in modern machine learning can be formulated as finding equilibria in \emph{sequential} games. In particular, two-player zero-sum sequential games, also known as minimax optimization, have received growing interest. It is tempting to apply gradient descent to solve minimax optimization given its popularity a…
Minimax defense improves neural network security against gradient-based attacks.
problem Gradient-based adversarial attacks on neural networks.
method Minimax optimization in a GAN framework to create a discriminator that plays a minimax game with the generator.
result Minimax defense significantly reduces adversarial attack success rates compared to standard classifiers.
Adversarial meta-learning computes Gamma-minimax estimators for vague prior knowledge.
problem Estimating parameters with vague prior knowledge.
method Adversarial meta-learning algorithms for Gamma-minimax estimators.
result Convergence guarantees and neural network class for selection.
New bounds on minimax regret for sequential probability assignment using logarithmic loss.
problem Minimizing regret in sequential probability assignment against arbitrary experts.
method Using self-concordance property of logarithmic loss to derive tight bounds.
result Tight bounds on minimax regret for various expert classes.
Classical scaling is shown to be optimal under various noisy conditions.
problem Consistency of classical scaling under general noise conditions.
method Established using finite fourth moments of noise, derived convergence rates, and matching minimax lower bounds.
result Classical scaling achieves minimax optimality in recovering true configuration from noisy dissimilarities.
MRCpy implements minimax risk classifiers with performance guarantees and distribution shift adaptability.
problem Classical risk minimization approaches are not robust to distribution shifts.
method Robust risk minimization approach for minimax risk classifiers.
result MRCs provide performance guarantees and adapt to distribution shifts.
Given a task of predicting Y Y Y from X X X , a loss function L L L , and a set of probability distributions Γ Γ Γ on ( X , Y ) (X,Y) ( X , Y ) , what is the optimal decision rule minimizing the worst-case expected loss over Γ Γ Γ ? In this paper, we address this question by introducing a generalization of the principle of maximum entropy. Applying t…
We prove a new minimax theorem connecting the worst-case Bayesian regret and minimax regret under partial monitoring with no assumptions on the space of signals or decisions of the adversary. We then generalise the information-theoretic tools of Russo and Van Roy (2016) for proving Bayesian regret bounds and combine th…
Study reveals differences in label shift problem difficulty in supervised vs. unsupervised settings.
problem Label shift problem in non-parametric classification.
method Analysis of minimax rates in supervised and unsupervised settings, focusing on class conditional distributions estimation.
result A class proportion estimation approach is minimax rate-optimal in the unsupervised setting.
Study minimax linear regression under quantile risk, improving existing bounds and providing new results.
problem Designing minimax procedures in linear regression under quantile risk.
method Analyzes realizable setting with Gaussian noise, extends to all p-th power error functions, develops new lower and upper bounds.
result Proves minimaxity of a variant of the min-max regression procedure for all p-th power error functions.
New RL algorithm minimizes distributional learning error.
problem Improving distributional reinforcement learning for better error minimization.
method Proposes a new model-based algorithm with theoretical minimax optimality.
result Proves minimax optimality for approximating return distributions.
Paper defends machine learning models from adversarial attacks using GLRT.
problem Adversarial attacks on machine learning models leading to misclassification.
method Generalized likelihood ratio test (GLRT) for robust classification.
result GLRT yields performance competitive with minimax approach under worst-case attacks, and better trade-off under weaker attacks.
MOTS improves Thompson sampling to match minimax bounds for bandit problems.
problem Achieving optimal regret bounds for Thompson sampling in multi-armed bandit problems.
method Proposes MOTS, a variant of Thompson sampling that clips arm sampling.
result Proves MOTS achieves minimax optimal regret bounds O ( K T ) O(\sqrt{KT}) O ( K T ) . It is generally believed that ensemble approaches, which combine multiple algorithms or models, can outperform any single algorithm at machine learning tasks, such as prediction. In this paper, we propose Bayesian convex and linear aggregation approaches motivated by regression applications. We show that the proposed a…
Develops a new test for comparing two groups' densities, showing minimax optimality.
problem Comparing probability densities between two groups.
method Probabilistic tensor product smoothing spline framework for joint density modeling; penalized likelihood ratio test for interaction testing.
result Proposed test is minimax optimal and outperforms conventional approaches.
Study confirms optimal minimax rate for nonlocal interaction kernel estimation.
problem Estimating nonlocal interaction kernels in interacting particle systems.
method Introduced tamed least squares estimator (tLSE) achieving optimal convergence rate.
result Optimal minimax rate of convergence confirmed for β ≥ 1 / 4 β \geq 1/4 β ≥ 1/4 . Private two-sample tests under LDP achieve minimax rates for multinomial and continuous data.
problem Achieving statistical utility while maintaining privacy in two-sample testing.
method Private permutation tests for multinomial data and adaptive tests for continuous data.
result Minimax optimal tests for private two-sample testing under LDP.
New approach transfers rewards learned in one environment to reinforcement learning in a new environment.
problem Transfer of rewards learned using inverse reinforcement learning from one environment to a new, different environment.
method Formulate the problem as a joint system of Bellman equations, develop minimax estimators for the target soft- q q q -function, solve the source and target system of equations jointly. result The coupled approach removes the first-order influence of source Bellman residual error compared to the sequential approach.
GL-LowPopArt improves minimax-optimal estimation for trace regression.
problem Minimizing estimation error in generalized low-rank trace regression.
method Two-stage approach: nuclear norm regularization followed by matrix Catoni estimation.
result Achieves instance-wise optimal error bounds up to condition number.
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…
ConquerNet smooths quantile regression for deep learning with minimax guarantees.
problem Optimization challenges in quantile regression for deep models.
method ConquerNet uses convolution-smoothed quantile ReLU neural networks.
result ConquerNet provides minimax guarantees and outperforms standard quantile neural networks.
Develops GLRT for defending against adversarial attacks in hypothesis testing.
problem Adversarial attacks on machine learning models causing misclassification.
method Generalized likelihood ratio test applied to composite hypothesis testing problem.
result GLRT approach yields competitive robustness-accuracy tradeoff under various attacks.
This work optimizes identifying good arms in nonparametric multi-armed bandits.
problem Efficiently identifying arms with high means in nonparametric settings.
method Combining reward-maximizing sampling with a nonparametric sequential test for anytime-valid labeling.
result Achieves minimax optimal stopping times for identifying arms above a threshold.
New SGDA method speeds up nonconvex minimax optimization.
problem Improving convergence of nonconvex minimax optimization.
method SGDA with random reshuffling for nonconvex-PŁ objectives.
result Convergence rates faster than with-replacement SGDA.
Measuring the similarity of two files is an important task in malware analysis, with fuzzy hash functions being a popular approach. Traditional fuzzy hash functions are data agnostic: they do not learn from a particular dataset how to determine similarity; their behavior is fixed across all datasets. In this paper, we …
We study online convex optimization under stochastic sub-gradient observation faults, where we introduce adaptive algorithms with minimax optimal regret guarantees. We specifically study scenarios where our sub-gradient observations can be noisy or even completely missing in a stochastic manner. To this end, we propose…
Proves minimax sample complexity for turn-based stochastic games.
problem Proving theoretical guarantees for reinforcement learning in turn-based stochastic games.
method Developing absorbing TBSG and reward perturbation techniques to handle statistical dependence.
result Empirical Nash equilibrium strategy approximates true Nash equilibrium in turn-based stochastic games.
Neural networks minimize error with shallow ReLU models for function estimation.
problem Estimating unknown functions from noisy data.
method Minimizing squared errors plus weight decay regularization.
result Neural network estimators are minimax optimal up to logarithmic factors.
MOSAIC detects change points in dynamic networks with low-rank and sparse changes.
problem Detecting change points in dynamic networks with specific structural properties.
method Eigen-decomposition-based test with screened signals and residual-based adjustment.
result MOSAIC achieves minimax-optimal detection and testing rates.
The paper analyzes reinforcement learning methods for estimating weights and quality functions with fast convergence rates.
problem Estimating weights and quality functions in reinforcement learning with function approximation.
method The paper uses minimax methods for estimating marginal importance weights and q-functions.
result The minimax approach enables fast rates of convergence for weights and quality functions, achieving first-order efficiency.
New methods solve complex optimization problems without strong convexity assumptions.
problem Complex bilevel optimization problems with minimax lower-level structures.
method Penalty-based first-order methods for bilevel minimax optimization.
result Achieves ε ε ε -KKT point with improved oracle complexity. Score attack method provides a lower bound on privacy-constrained minimax risk.
problem Characterizing the optimality of privacy-constrained statistical models.
method Score attack based on tracing attack concept.
result Optimally lower bounds the minimax risk of estimating unknown model parameters.
Two new algorithms solve nonconvex-strongly concave problems efficiently.
problem Solving nonconvex-strongly concave minimax problems.
method Proposed MINIMAX-TR and MINIMAX-TRACE algorithms.
result Find ( ε , ε ) (ε, \sqrtε) ( ε , ε ) -second order stationary points within O ( ε − 1.5 ) \mathcal{O}(ε^{-1.5}) O ( ε − 1.5 ) iterations. The paper tackles robust policy learning from multiple data sources.
problem Learning a policy that generalizes across diverse settings from multiple heterogeneous data sources.
method Proposes a minimax regret optimization objective and a policy learning algorithm combining doubly robust offline policy evaluation and no-regret learning.
result Achieves minimal worst-case mixture regret up to a moderated vanishing rate of the total data across all sources.
Paper develops a method for estimating PFLM with minimized rates in high dimensions.
problem Estimating PFLM with minimized rates in high dimensions.
method Least square approach with mixed regularizations of function-norm and ℓ1-norm.
result Established optimal minimax rates of estimation for PFLM.
New algorithm solves nonconvex-convex minimax problems efficiently.
problem Solving nonconvex-convex minimax problems with nonsmooth, nonconvex, and nonlinearity.
method Hybrid variance-reduced SGD algorithm combining smoothing and biased techniques.
result Achieves O(T^(-2/3)) convergence rate and best oracle complexity.
This work provides a simplified proof of the statistical minimax optimality of (iterate averaged) stochastic gradient descent (SGD), for the special case of least squares. This result is obtained by analyzing SGD as a stochastic process and by sharply characterizing the stationary covariance matrix of this process. The…
Paper develops a minimax optimal test for goodness-of-fit using kernel Stein discrepancy.
problem Developing a robust goodness-of-fit test for general domains.
method Kernel Stein Discrepancy (KSD) with spectral regularization and adaptive testing.
result Proposed regularized test achieves minimax optimality up to a logarithmic factor.
Unified analysis of efficient local training methods for distributed variational inequalities.
problem Efficient distributed/federated learning for variational inequality problems.
method Unified convergence analysis of communication-efficient local training methods.
result First local gradient descent-accent algorithms with improved communication complexity.
Incremental clustering approaches have been proposed for handling large data when given data set is too large to be stored. The key idea of these approaches is to find representatives to represent each cluster in each data chunk and final data analysis is carried out based on those identified representatives from all t…
Study stabilizes adversarial training in neural networks over infinite-dimensional spaces.
problem Stability issues in adversarial training of neural networks.
method Functional analysis of minimax optimization over infinite-dimensional spaces of continuous functions and probability measures.
result Convergence property of minimax problems under certain conditions, interpreted as stabilization techniques.
EQO uses a simple bonus term for efficient exploration in tabular RL.
problem Achieving minimax optimal reinforcement learning with practical efficiency.
method Exploration via Quasi-Optimism, employing a bonus proportional to state-action visit count.
result Achieves the sharpest known regret bound for tabular RL.
A novel decentralized algorithm improves minimax optimization in federated learning.
problem Minimax optimization in federated learning with data heterogeneity.
method Decentralized Gradient Tracking (K-GT-Minimax) for nonconvex-strongly-concave optimization.
result Demonstrates superior convergence rate for NC-SC minimax optimization.
A robust method for off-policy evaluation in contextual bandits.
problem Evaluating policies when direct methods are unavailable.
method Robust regression approach to off-policy evaluation.
result Superior empirical performance across benchmarks.
Paper proposes a federated learning framework for relative fairness.
problem Traditional fairness in federated learning overlooks performance disparities between client subgroups.
method Uses a minimax problem approach to minimize relative unfairness, introducing a fairness index based on loss ratios.
result Empirical evaluations confirm the framework's effectiveness in maintaining model performance while reducing disparity.
Efficient strategies for online learning against bandit algorithms solve minimax problems.
problem Solving min-max problems in convex-linear settings with empirical distributions.
method Designing online learning algorithms that play against bandit algorithms, leveraging properties of the set of empirical distributions.
result High-probability convergence guarantees to minimax values for a specific family of sets.
New statistical framework for coresets in density estimation.
problem Improving computational efficiency in density estimation.
method Developed a statistical framework for coresets in nonparametric density estimation.
result Practical coreset kernel density estimators are near-minimax optimal.