Paper analyzes minimax regret in constrained online convex optimization with limited switching opportunities.
problem Minimizing regret in online convex optimization with limited switching opportunities.
method Introduced fugal game relaxation and mini-batching algorithm to establish minimax regret bounds.
result Minimax regret of switching-constrained OCO is Θ(T / √K).
New algorithm solves minimax games with linear constraints.
problem Nonconvex minimax games with coupled linear constraints.
method Primal-dual alternating proximal gradient (PDAPG) algorithm.
result Achieves ε-stationary solution within O(ε^(-2)) iterations for strongly concave settings.
Generative Adversarial Privacy (GAP) learns privacy mechanisms from data.
problem Learning optimal privacy mechanisms from data.
method Formulates privacy as a constrained minimax game between privatizer and adversary.
result GAP provides privacy guarantees against strong adversaries.
New classifier avoids unfair treatment using robust log loss.
problem Ensuring fairness in classification models for social applications.
method Derives a new classifier from distributional robustness, incorporating fairness criteria into worst-case logarithmic loss minimization.
result Shows practical advantages in three fairness datasets.
This paper analyzes saddle points and minimax points in non-convex smooth games.
problem Understanding local optimal points in non-convex smooth games.
method Comprehensive analysis of local minimax points, including their optimality conditions and stability.
result Local saddle points are uniformly local minimax points under mild continuity assumptions.
A new method solves complex constrained minimax problems.
problem Solving constrained minimax optimization problems.
method First-order augmented Lagrangian method.
result Established an operation complexity of O ( ε − 4 log ε − 1 ) O(\varepsilon^{-4}\log\varepsilon^{-1}) O ( ε − 4 log ε − 1 ) . Negative momentum accelerates convergence in minimax games but at a suboptimal rate.
problem The convergence rate of negative momentum in minimax games is suboptimal.
method Extending variational inequality formulation, connecting momentum method with Chebyshev polynomials.
result Negative momentum accelerates convergence locally but at a suboptimal rate.
A new algorithm calculates optimal strategies for two-player zero-sum games.
problem Computing the optimal strategies for two-player zero-sum games.
method Extending successive relaxation to two-player zero-sum games and developing a generalized minimax Q-learning algorithm.
result The proposed algorithm converges and effectively computes optimal strategies.
Paper explains adversarial training's robust overfitting through a minimax game perspective.
problem Adversarial training suffers from robust overfitting after learning rate decay.
method Viewing adversarial training as a dynamic minimax game, analyzing how LR decay breaks balance and leads to overfitting.
result ReBalanced Adversarial Training (ReBAT) alleviates robust overfitting without sacrificing robustness.
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.
Improved FTPL algorithm reduces regret in predictable minimax games.
problem Online learning and minimax games with predictable loss sequences.
method Optimistic modification of FTPL with dual regularization view.
result Tighter regret bounds for predictable sequences, O ( T − 1 / 2 ) O(T^{-1/2}) O ( T − 1/2 ) accuracy. Paper defines local optimality for sequential nonconvex-nonconcave games.
problem Defining local optimality in sequential nonconvex-nonconcave minimax optimization.
method Proposes local minimax definition and connects to gradient descent ascent.
result Gradient descent ascent stable limit points are local minimax points.
New algorithms solve nonconvex-nonconcave minimax optimization problems.
problem Solving minimax optimization problems in machine learning.
method Two novel Newton-type algorithms for nonconvex-nonconcave minimax optimization.
result Proved local convergence at strict local minimax points.
Study tests feasibility of linear programs with bandit feedback.
problem Testing feasibility of unknown linear programs with bandit feedback.
method Developed a novel test based on low-regret algorithms and a nonasymptotic law of iterated logarithms.
result Proved that the test is reliable and adapts to the signal level, with mean sample costs scaling as \( \widetilde{O}(d^2/Γ^2) \).
A new method solves a complex optimization problem efficiently.
problem Nonconvex-strongly-concave constrained minimax optimization.
method First-order augmented Lagrangian method with a first-order subproblem solver.
result Achieves improved operation complexity for finding solutions.
Optimal online learning algorithms for label-efficient prediction and bandits.
problem Efficient prediction in online learning with limited information.
method Optimistic online mirror descent with second order corrections and hybrid regularizers.
result Improved regret bounds for label-efficient prediction and bandits.
New theorem guarantees approximate equilibrium in non-convex games.
problem No guarantee of equilibrium in non-convex games.
method Introduced a minimax theorem for non-convex games involving neural networks.
result Provided an approximate minimax theorem for non-convex games.
We find the optimal error for a constrained regression model under a linear model.
problem Minimizing error while adhering to demographic parity constraints.
method Proposed a minimax optimal error analysis for a demographic parity-constrained regression problem within a linear model.
result The minimax optimal error is characterized by $Θ( rac{dM}{n})$ .
Paper proposes FR algorithm to solve minimax optimization locally.
problem Gradient descent fails to find local minimax in minimax optimization.
method Follow-the-Ridge (FR) algorithm, addressing rotational behavior of gradient dynamics.
result FR algorithm provably converges to local minimax.
New method solves complex constrained optimization problems.
problem Constrained nonconvex-nonconcave minimax optimization problems.
method Inexact proximal gradient method using sequential convex programming.
result Established complexity guarantees for approximate stationary points.
New minimax theorem connects Bayesian and minimax regret in partial monitoring.
problem Minimax regret in partial monitoring with no assumptions on adversary.
method Information-theoretic tools and minimax theorem.
result Clean analysis of easy and hard finite partial monitoring with new bounds.
Alt-GDA outperforms Sim-GDA in minimax games with near-optimal local convergence.
problem Minimax optimization convergence rate comparison
method Alternating Gradient Descent-Ascent (Alt-GDA) vs. Simultaneous Gradient Descent-Ascent (Sim-GDA)
result Alt-GDA achieves near-optimal local convergence rate for strongly convex-strongly concave problems, while Sim-GDA converges slower.
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…
New bounds show simple predictors can learn complex concepts online.
problem When can simple predictors learn complex concepts in online learning?
method Characterized optimal mistake bounds for online learning with simple predictors.
result Achieved nearly optimal mistake bounds for online learning using sparse majority-vote of proper predictors.
Paper studies constrained control games with a novel approximation method.
problem Games with constrained control directions.
method Approximation procedure based on L 1 L^1 L 1 -stability estimates and almost sure convergence. result Existence of game's value and optimal strategy for the stopper.
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.
A new game-theoretic approach optimizes complex rate metrics.
problem Optimizing non-decomposable performance metrics and rate constraints.
method Extending two-player game approaches to a three-player game, seeking equilibrium.
result Generalizes and improves upon existing algorithms for constrained optimization.
Unified framework for Bayesian and Frequentist statistics.
problem Embedding Bayesian statistics within a broader decision-making framework.
method Game theory and statistical analysis.
result Statistical games unify Bayesian and Frequentist statistics.
Algorithm reduces regret in complex game scenarios.
problem Complex game scenarios with partial monitoring.
method Simple and efficient algorithm for minimax regret.
result Regret bound of 6 ( d + 1 ) k 3 / 2 n log ( k ) 6(d+1) k^{3/2} \sqrt{n \log(k)} 6 ( d + 1 ) k 3/2 n log ( k ) . 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…
Bayesian methods suffer from the problem of how to specify prior beliefs. One interesting idea is to consider worst-case priors. This requires solving a stochastic zero-sum game. In this paper, we extend well-known results from bandit theory in order to discover minimax-Bayes policies and discuss when they are practica…
Paper finds algorithms with both low regret and high exploitation.
problem Finding algorithms with both low regret and high exploitation.
method Investigates online learning algorithms with bandit feedback.
result First affirmative answer to guaranteeing both O ( 1 ) O(1) O ( 1 ) regret and i l d e O ( T ) ilde{O}(\sqrt{T}) i l d e O ( T ) regret. KG-A2C agent learns natural language IF games by reasoning and constraining action spaces.
problem Challenges of natural language understanding, partial observability, and combinatorially large action spaces in IF games.
method Builds a dynamic knowledge graph while exploring, constraining actions using templates.
result Outperforms current IF agents across various games with larger action spaces.
A new method trains physics-constrained neural networks more efficiently.
problem Training machine learning tools with limited data and physical constraints.
method Dual-Dimer method for searching saddle points in nonconvex-nonconcave functions.
result The Dual-Dimer method improves training efficiency and convergence speed.
The paper explores the information-theoretic nature of excess risk in machine learning.
problem Understanding the excess risk in machine learning models.
method Formulates the minimax excess risk as a zero-sum game and modifies it to allow swapping of the order of play.
result Proves that under certain conditions, the duality gap is zero, allowing for the application of Bayesian results to provide bounds on minimax excess risk.
New algorithms for private GLM estimation with minimax lower bounds.
problem Privacy in generalized linear models.
method Differentially private algorithms using projected gradient descent.
result Nearly rate-optimal performance with privacy-constrained minimax lower bounds.
Develops a convex duality framework for analyzing GANs.
problem Analyzing how GANs behave under different discriminator constraints.
method Introduces a convex duality framework to interpret GANs under constrained discriminators.
result Shows that the GAN formulation can be interpreted as minimizing a divergence to penalized moments of the data distribution.
Paper learns skill distributions from game outcomes, proving minimax optimality.
problem Learning skill distributions from noisy pairwise game outcomes.
method Proposes a simple algorithm using kernel density estimation and minimax techniques.
result Near-optimal minimax mean squared error scaling for skill density estimation.
Fuzzy hashes learn from data to improve file similarity detection.
problem Measuring similarity between files, especially malware.
method Learned fuzzy hashes using a minimax training framework.
result Learned fuzzy hashes outperform traditional methods for file similarity.
We consider a symmetric multi-players zero-sum game with two strategic variables. There are n n n players, n ≥ 3 n\geq 3 n ≥ 3 . Each player is denoted by i i i . Two strategic variables are t i t_i t i and s i s_i s i , i ∈ { 1 , … , n } i\in \{1, \dots, n\} i ∈ { 1 , … , n } . They are related by invertible functions. Using the minimax theorem by \cite{sion} we will show that Nas…
New ranking system balances fairness and user utility.
problem Achieving group fairness in ranking systems.
method Formulated a minimax game between a ranking player and an adversary.
result Better utility for highly fair rankings.
Competition has been introduced in the electricity markets with the goal of reducing prices and improving efficiency. The basic idea which stays behind this choice is that, in competitive markets, a greater quantity of the good is exchanged at a lower and a lower price, leading to higher market efficiency. Electricity …
Theoretical analysis of DQN and its variants.
problem Understanding the theoretical foundations of deep Q-learning.
method Theoretical analysis of DQN and Minimax-DQN algorithms under mild assumptions.
result Established rates of convergence for action-value functions and provided justifications for DQN techniques.
Paper optimizes multi-agent learning in Markov games with generative model.
problem Learning Nash or CCE equilibria in multi-agent Markov games.
method Develops \myalg~algorithm and adaptive sampling scheme using FTRL method.
result Minimax-optimal learning of CCE with minimal samples.
We consider in this paper the problem of noisy 1-bit matrix completion under a general non-uniform sampling distribution using the max-norm as a convex relaxation for the rank. A max-norm constrained maximum likelihood estimate is introduced and studied. The rate of convergence for the estimate is obtained. Information…
OMWU shows last iterate convergence in convex-concave games.
problem Optimizing in constrained min-max optimization landscapes.
method OMWU (Optimistic Multiplicative-Weights Update) in the no-regret online learning framework.
result OMWU exhibits last iterate convergence for convex-concave games, generalizing previous results.
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.
Pessimistic Minimax Value Iteration finds efficient NE policies from offline data.
problem Finding an approximate Nash equilibrium in offline Markov games with non-uniform coverage.
method Pessimistic Minimax Value Iteration (PMVI) constructs pessimistic value function estimates and solves NEs.
result Established a nearly minimax optimal result for offline Markov games with function approximation.