arXiv research

Last iterate of Extragradient algorithm converges slower than averaged iterates in saddle point problems.

New saddle network architectures preserve convex-concave geometry in optimization problems.

We consider the convex-concave saddle point problem $\min_{x}\max_{y} f(x)+y^\top A x-g(y)$ 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…

As has been observed by Morse \cite{Mo}, any generic vector field $v$ on a compact smooth manifold $X$ with boundary gives rise to a stratification of the boundary $\d X$ by compact submanifolds $\{\d_j^\pm X(v)\}_{1 \leq j \leq \dim(X)}$, where $\textup{codim}(\d_j^\pm X(v))= j$. Our main observation is that this stra…

Riemannian algorithms converge at Euclidean rates for geodesically convex-concave problems.

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 …

Improved algorithms for convex-concave min-max optimization and monotone variational inequalities.

Paper improves algorithms for convex-concave minimax optimization problems.

We define a class of L-convex-concave subsets of $\Bbb{R}P^n$, where L is a projective subspace of dimension l in $\Bbb{R}P^n$. These are sets whose sections by any (l+1)-dimensional space L' containing L are convex and concavely depend on L'. We introduce an L-duality for these sets, and prove that the L-dual to an L-…

Gradient Descent Ascent converges to von-Neumann solution in hidden zero-sum games.

Paper establishes lower bounds for finite-sum optimization problems using novel construction methods.

We study the iteration complexity of the optimistic gradient descent-ascent (OGDA) method and the extra-gradient (EG) method for finding a saddle point of a convex-concave unconstrained min-max problem. To do so, we first show that both OGDA and EG can be interpreted as approximate variants of the proximal point method…

A generalized optimistic method for saddle point problems with improved complexity.

OMWU shows last iterate convergence in convex-concave games.

PURE-CD algorithm proves complexity bounds for convex-concave problems.

ICCNLS models complex relationships as convex and concave components.

Paper introduces $\ell$-DER for regression tasks using morphological operators and convex-concave procedure.

New method finds arbitrage opportunities in fluctuating asset bands.

Paper solves minimax optimization gap with near-optimal algorithms.

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

We define a class of $L$-convex-concave subsets of $\mathbb{R}P^3$, where $L$ is a projective line in $\mathbb{R}P^3$. These are sets whose sections by any plane containing $L$ are convex and concavely depend on this plane. We prove a version of Arnold hypothesis for these sets, namely we prove that each such set conta…

While classic work in convex-concave min-max optimization relies on average-iterate convergence results, the emergence of nonconvex applications such as training Generative Adversarial Networks has led to renewed interest in last-iterate convergence guarantees. Proving last-iterate convergence is challenging because ma…

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…

New algorithm AG-OG optimizes separable convex-concave problems efficiently.

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…

Optimistic method adapted for faster convex-concave min-max problems.

A new algorithm solves minimax problems without needing parameters.

Sparse additive modeling is a class of effective methods for performing high-dimensional nonparametric regression. In this work we show how shape constraints such as convexity/concavity and their extensions, can be integrated into additive models. The proposed sparse difference of convex additive models (SDCAM) can est…

New algorithm solves non-convex, non-differentiable min-max games.

Optimizes bond portfolios to avoid worst-case losses.

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…

RO-TD learns sparse value functions efficiently.

We consider the use of no-regret algorithms to compute equilibria for particular classes of convex-concave games. While standard regret bounds would lead to convergence rates on the order of $O(T^{-1/2})$, recent work \citep{RS13,SALS15} has established $O(1/T)$ rates by taking advantage of a particular class of optimi…

This paper analyzes stability and generalization of Markov chain stochastic gradient methods.

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…

This paper analyzes saddle points and minimax points in non-convex smooth games.

APAC-Net solves high-dimensional stochastic MFGs using neural networks.

New algorithms ensure reproducibility and optimal convergence in convex optimization.

Gradient methods converge exponentially in concave network games.

Paper proves Sion's theorem in geodesic spaces and develops a Riemannian extragradient method.

We consider the evolution of hypersurfaces on the unit sphere $\mathbb{S}^{n+1}$ by smooth functions of the Weingarten map. We introduce the notion of `quasi-ancient' solutions for flows that do not admit non-trivial, convex, ancient solutions. Such solutions are somewhat analogous to ancient solutions for flows such a…

New algorithm solves saddle point problems in Banach spaces.

Partial label learning deals with the problem where each training instance is assigned a set of candidate labels, only one of which is correct. This paper provides the first attempt to leverage the idea of self-training for dealing with partially labeled examples. Specifically, we propose a unified formulation with pro…

We solve a complex optimization problem for Wasserstein barycenters using stochastic methods.

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…

We consider the problem of minimizing a smooth convex function by reducing the optimization to computing the Nash equilibrium of a particular zero-sum convex-concave game. Zero-sum games can be solved using online learning dynamics, where a classical technique involves simulating two no-regret algorithms that play agai…

GradientDICE improves offline estimation for reinforcement learning policies.

This work analyzes how overparameterization aids GANs in reaching global saddle points.