Last iterate of Extragradient algorithm converges slower than averaged iterates in saddle point problems.
problem Smooth convex-concave saddle point problems
method Analysis of Extragradient (EG) algorithm convergence rates
result The last iterate of EG converges at a rate of O(1/√T), compared to O(1/T) for averaged iterates
New saddle network architectures preserve convex-concave geometry in optimization problems.
problem Optimization models with convex x and concave y components.
method Structured separable decomposition and saddle network architectures.
result Proven one-dimensional approximation theorem and high accuracy on various test functions.
A generalized optimistic method for saddle point problems with improved complexity.
problem Solving convex-concave saddle point problems efficiently.
method Proposes a generalized optimistic method that includes the optimistic gradient method as a special case, handling constrained saddle point problems with composite objective functions and arbitrary norms.
result Best-known global iteration complexity bounds for first-, second-, and higher-order methods.
Optimizes bond portfolios to avoid worst-case losses.
problem Finding the worst-case value of a bond portfolio over a range of yield curves and spreads.
method Solves a convex-concave saddle point optimization problem to find the worst-case value and construct a robust portfolio.
result Constructs a bond portfolio that includes the worst-case value, ensuring robustness against market uncertainties.
We consider convex-concave saddle point problems with a separable structure and non-strongly convex functions. We propose an efficient stochastic block coordinate descent method using adaptive primal-dual updates, which enables flexible parallel optimization for large-scale problems. Our method shares the efficiency an…
We consider the convex-concave saddle point problem minxmaxyf(x)+y⊤Ax−g(y) where f is smooth and convex and g is smooth and strongly convex. We prove that if the coupling matrix A has full column rank, the vanilla primal-dual gradient method can achieve linear convergence even if f is not stron…
New analysis shows convergence rate of 1/k for gradient and extra-gradient methods.
problem Finding saddle points in convex-concave problems.
method Interpreted as proximal point method approximations, showing iterates remain bounded.
result Primal dual gap converges at rate O(1/k).
We reformulate LIPs as min-max problems for easier solution.
problem Recovering signals from few linear measurements.
method Proposed a min-max reformulation of LIPs.
result Saddle points characterize solutions to LIPs.
We solve a complex optimization problem for Wasserstein barycenters using stochastic methods.
problem Optimizing the average of multiple probability distributions in a streaming data setting.
method We reformulate the problem as a convex-concave saddle-point problem and propose a stochastic optimization algorithm.
result Our algorithm has better complexity than existing methods for arbitrary distributions.
DualIV simplifies non-linear IV regression via dual formulation.
problem Non-linear instrumental variable regression with potential first-stage regression bottleneck.
method Dual formulation of non-linear IV regression as a convex-concave saddle-point problem, leading to a kernel-based algorithm with analytic solution.
result Empirical results show competitive performance compared to existing algorithms.
New algorithm speeds up solving saddle-point problems with large condition numbers.
problem Solving saddle-point problems with large condition numbers.
method Proposes a stochastic proximal point algorithm that accelerates variance reduction methods.
result Reduces logarithmic term of condition number for iteration complexity.
We extend the Frank-Wolfe (FW) optimization algorithm to solve constrained smooth convex-concave saddle point (SP) problems. Remarkably, the method only requires access to linear minimization oracles. Leveraging recent advances in FW optimization, we provide the first proof of convergence of a FW-type saddle point solv…
APAC-Net solves high-dimensional stochastic MFGs using neural networks.
problem High-dimensional stochastic mean-field games.
method Alternating population and control neural networks, parameterizing value and density functions.
result Solves up to 100-dimensional MFG problems.
New method optimizes data from correlated time series using robust optimization.
problem Optimizing with non-i.i.d. vector autoregressive data.
method Distributionally robust optimization with Wasserstein distance.
result Method is equivalent to a convex-concave saddle point problem.
New method stabilizes saddle-point optimization with unbounded gradients.
problem Stochastic saddle-point optimization faces instability due to large gradients.
method Proposes a regularization technique to stabilize iterates.
result Yields meaningful performance guarantees even with unbounded gradients.
We consider variational inequalities coming from monotone operators, a setting that includes convex minimization and convex-concave saddle-point problems. We assume an access to potentially noisy unbiased values of the monotone operators and assess convergence through a compatible gap function which corresponds to the …
We study the online saddle point problem, an online learning problem where at each iteration a pair of actions need to be chosen without knowledge of the current and future (convex-concave) payoff functions. The objective is to minimize the gap between the cumulative payoffs and the saddle point value of the aggregate …
New algorithm solves saddle point problems in Banach spaces.
problem Solving saddle point problems in real reflexive Banach spaces.
method Stochastic Bregman Primal-Dual Splitting Algorithm with relative smoothness and strong convexity assumptions.
result Almost sure convergence to saddle points under various conditions.
We consider a generic convex-concave saddle point problem with separable structure, a form that covers a wide-ranged machine learning applications. Under this problem structure, we follow the framework of primal-dual updates for saddle point problems, and incorporate stochastic block coordinate descent with adaptive st…
Despite the success of single-agent reinforcement learning, multi-agent reinforcement learning (MARL) remains challenging due to complex interactions between agents. Motivated by decentralized applications such as sensor networks, swarm robotics, and power grids, we study policy evaluation in MARL, where agents with jo…
This work analyzes how overparameterization aids GANs in reaching global saddle points.
problem Understanding the role of overparameterization in GANs for convergence to global saddle points.
method Theoretical and empirical analysis of overparameterized GANs with various architectures and datasets.
result GDA converges to a global saddle point in overparameterized GANs with certain assumptions.
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.
We study the global convergence of generative adversarial imitation learning for linear quadratic regulators, which is posed as minimax optimization. To address the challenges arising from non-convex-concave geometry, we analyze the alternating gradient algorithm and establish its Q-linear rate of convergence to a uniq…
Decentralized method solves saddle point problems with theoretical guarantees.
problem Solving saddle point problems in a decentralized network.
method Proximal point method adapted for decentralized networks.
result Converges to approximate stationarity with rate of O(1/√T).
Riemannian algorithms converge at Euclidean rates for geodesically convex-concave problems.
problem Min-max optimization on Riemannian manifolds.
method RCEG method and RGDA for geodesically strongly-convex-concave problems.
result RCEG achieves linear convergence rate in geodesically strongly-convex-concave cases.
In this paper we propose a primal-dual proximal extragradient algorithm to solve the generalized Dantzig selector (GDS) estimation problem, based on a new convex-concave saddle-point (SP) reformulation. Our new formulation makes it possible to adopt recent developments in saddle-point optimization, to achieve the optim…
Policy evaluation is a crucial step in many reinforcement-learning procedures, which estimates a value function that predicts states' long-term value under a given policy. In this paper, we focus on policy evaluation with linear function approximation over a fixed dataset. We first transform the empirical policy evalua…
Paper tackles AUC maximization with deep neural networks for better classification of imbalanced data.
problem Stochastic AUC maximization with deep neural networks for better fit to imbalanced data classification.
method Saddle point reformulation of a surrogated loss of AUC, non-convex concave min-max problem, Polyak-Łojasiewicz (PL) condition, AdaGrad-style algorithm.
result Effective algorithms developed with faster convergence rate and adaptive step size scheme.
Owing to their connection with generative adversarial networks (GANs), saddle-point problems have recently attracted considerable interest in machine learning and beyond. By necessity, most theoretical guarantees revolve around convex-concave (or even linear) problems; however, making theoretical inroads towards effici…
Optimal privacy-preserving algorithm for solving saddle point problems.
problem Solving convex-concave stochastic saddle point problems under differential privacy constraints.
method Recursive regularization technique repurposed for saddle point problems, achieving strong gap rate of O(1/√n + √d/nε).
result Achieves nearly optimal strong gap rate of O(1/√n + √d/nε) with gradient complexity O(min{n^2ε^(1.5)/√d, n^(3/2)}).
Paper proves Sion's theorem in geodesic spaces and develops a Riemannian extragradient method.
problem Understanding saddle points in nonconvex-nonconcave minimax problems.
method Geodesic metric space version of Sion's theorem and Riemannian extragradient method.
result Developed a Riemannian extragradient algorithm for smooth minimax problems.
Many problems in machine learning and game theory can be formulated as saddle-point problems, for which various first-order methods have been developed and proven efficient in practice. Under the general convex-concave assumption, most first-order methods only guarantee an ergodic convergence rate, that is, the uniform…
New algorithm improves self-play reinforcement learning for competitive games.
problem Inefficient opponent selection in self-play reinforcement learning.
method Intelligently selects opponents based on adversarial rules derived from saddle point optimization.
result Algorithm converges to approximate equilibrium with high probability in convex-concave games.
New algorithm solves non-convex, non-differentiable min-max games.
problem Limited theoretical understanding of non-smooth min-max games.
method Proximal gradient descent-ascent algorithm for convex-strongly convex games.
result Algorithm converges to ε-Nash equilibrium with polynomial gradient evaluations.
GradientDICE improves offline estimation for reinforcement learning policies.
problem Estimating density ratios between target policy and sampling distributions in reinforcement learning.
method GradientDICE reparameterizes the optimization problem to avoid nonlinearity, ensuring convergence and consistency.
result GradientDICE is provably convergent and eliminates the need for nonlinearity in parameterization.
New algorithms reduce variance in solving complex mathematical problems.
problem Solving convex-concave saddle point problems, variational inequalities, and inclusions.
method Stochastic variance reduction for extragradient, forward-backward-forward, and forward-reflected-backward methods.
result All proposed methods converge with complexities matching or improving deterministic counterparts.
In reinforcement learning (RL) , one of the key components is policy evaluation, which aims to estimate the value function (i.e., expected long-term accumulated reward) of a policy. With a good policy evaluation method, the RL algorithms will estimate the value function more accurately and find a better policy. When th…
This work provides lower bounds for differentiable games and defines a new condition number.
problem Understanding the fundamental limits of convergence in differentiable games.
method The authors cast saddle-point and min-max problems as 2-player games and use tools from single-objective convex optimization to derive linear lower bounds for convex-concave games. They also introduce a new condition number for games.
result The authors provide linear lower bounds for differentiable games, including n-player games, and introduce a new condition number that captures the possibility of linear rates in games without strong convexity or concavity. New methods for federated learning reduce communication costs.
problem Efficiently solving optimization problems in a distributed setting.
method Developed two strategies for achieving consensus in federated learning: fixed number of local steps and randomized computations.
result Convergence analysis and experiments show benefits of the proposed methods.
RO-TD learns sparse value functions efficiently.
problem Learning sparse value functions efficiently.
method RO-TD integrates off-policy convergent gradient TD methods and online convex regularization.
result RO-TD learns sparse value functions with low computational complexity.
We consider empirical risk minimization of linear predictors with convex loss functions. Such problems can be reformulated as convex-concave saddle point problems, and thus are well suitable for primal-dual first-order algorithms. However, primal-dual algorithms often require explicit strongly convex regularization in …
Study on private algorithms for saddle point and variational inequalities, improving efficiency and applicability.
problem Private algorithms for solving saddle point and variational inequalities under differential privacy constraints.
method Developed a recursive regularization algorithm for both Euclidean and non-Euclidean setups, providing bounds on strong SP-gap and VI-gap.
result Achieved nearly optimal rates for strong SP-gap and VI-gap under (ε,δ)-differential privacy, applicable to various p,q setups. We consider a generic convex optimization problem associated with regularized empirical risk minimization of linear predictors. The problem structure allows us to reformulate it as a convex-concave saddle point problem. We propose a stochastic primal-dual coordinate (SPDC) method, which alternates between maximizing ov…
Paper analyzes algorithms for nonstationary saddle-point optimization problems.
problem Nonstationary saddle-point optimization problems in game theory, reinforcement learning, and machine learning.
method Proposes extragradient and Frank-Wolfe algorithms for online and bandit settings.
result Establishes sub-linear regret bounds for the proposed algorithms.
This paper tackles convex-submodular minimax problems in mixed continuous-discrete domains.
problem Convex-submodular minimax problems in mixed continuous-discrete domains.
method Introduces new notions of optimality and proposes iterative algorithms combining discrete and continuous optimization.
result Characterizes convergence rates, computational complexity, and quality of solutions for convex and monotone-submodular minimax problems.
Heavy-ball algorithms can always avoid saddle points with random initialization.
problem Optimizing nonconvex functions with saddle points.
method Developed a new mapping to interpret heavy-ball algorithms as iterations, proving they can escape saddle points.
result Heavy-ball algorithms can escape saddle points with random initialization.
New algorithm solves min-max optimization problems in a decentralized manner.
problem Solving min-max saddle point games in a decentralized and adaptive manner.
method Developed a decentralized adaptive momentum (DADAM3) algorithm for min-max optimization. result DADAM3 achieves non-asymptotic rates of convergence for finding Nash equilibrium points. FeDualEx tackles saddle point optimization in federated learning with composite objectives.
problem Saddle point optimization with constraints and non-smooth regularization in federated learning.
method Federated Dual Extrapolation (FeDualEx) algorithm for saddle point optimization and composite objectives.
result FeDualEx effectively solves saddle point optimization problems with composite objectives in federated learning.