arXiv subjects

Emmanouil-Vasileios Vlatakis-Gkaragkounis

Publications and source records attributed to Emmanouil-Vasileios Vlatakis-Gkaragkounis.

At least 19 recordsLinked to original sources

arXiv2026

On the Complexity of Finding Fixed Points for Set-Valued Contractions

In this paper, we study the computational complexity of finding fixed points for set-valued contractions. We first formulate a computational problem for Nadler's fixed-point theorem: Projected-Nadler, and prove that it is $\mathsf{CLS}$-complete by showing its equivalence to Continuous-LocalOpt. We then establish a stronger converse for Nadler's fixed point theorem that can be applied as a tool to analyze the convergence rate of set-valued basic iteration procedure. Finally, we reduce large-margin triplet stationarity problem to Projected-Nadler. Together with its $\mathsf{CLS}$-hardness introduced in [arXiv:2509.16898], this yields $\mathsf{CLS}$-completeness of large-margin triplet stationarity.

cs.CC↗

arXiv2026

Breaking $1/ε$ Barrier in Quantum Zero-Sum Games: Generalizing Metric Subregularity for Spectraplexes

Quantum zero-sum games are bilinear saddle-point problems over density matrices. We study how their semidefinite geometry governs last-iterate convergence beyond existing $O(1/\varepsilon)$ average-iterate guarantees [arXiv:2311.10859]. We establish a Holder error bound with a finite, game-dependent exponent for every finite-dimensional quantum zero-sum game. If the game admits an equilibrium with both states positive definite, this bound is linear. Under this hypothesis, matrix variants of Nesterov's iterative smoothing and optimistic gradient descent-ascent (OGDA) converge linearly to the Nash equilibrium set, with $O(\log(1/\varepsilon))$ iteration complexity. The proof establishes metric subregularity under this full-rank hypothesis despite the nonpolyhedral geometry of spectraplexes. We also characterize Nash equilibria in semidefinite games through slack operators, classifying strategic directions as essential, neutral, or non-essential. This trichotomy reduces to a classical-style dichotomy when every Nash equilibrium is strictly complementary, as ensured by our rank-nondegeneracy condition. Finally, by extending the quantal response equilibrium framework to spectraplex games, we prove a $\widetilde{O}(1/\varepsilon)$ last-iterate guarantee for optimistic matrix multiplicative weights update (OMMWU) when the Nash equilibrium is unique and both equilibrium states have full rank. We further show that any $O(\log(1/\varepsilon))$ last-iterate guarantee for OMMWU must depend on a natural game condition number and hence on the ambient dimensions. Experiments show that OGDA outperforms OMMWU in the regimes studied, leaving open which spectraplex games admit provably comparable acceleration for OMMWU.

cs.GT↗

arXiv2026

Average-and Last-Iterate Lower Bounds for Optimistic Matrix Mirror-Prox in Quantum Zero-Sum Games

Optimistic matrix mirror-prox (OMMP) computes $ε$-approximate Nash equilibria in quantum zero-sum games with an $O(1/\varepsilon)$ average-iterate guarantee [arXiv:2311.10859]. We investigate whether this dependence on accuracy is tight and whether geometric last-iterate convergence can be guaranteed. We study these questions through explicit games with one qubit per player. First, we prove an $Ω(1/\varepsilon)$ lower bound for the uniform-average output that includes the maximally mixed initial state, independently of the regularizer and step size. Second, we construct a fixed game on which optimistic gradient descent-ascent (OGDA), initialized at the maximally mixed state, has last-iterate Frobenius distance to equilibrium $Θ(1/t)$ and duality gap $Θ(1/t^3)$ for every sufficiently small fixed step size. A separate fixed game exhibits arbitrarily long delays in reducing the initial error by a constant factor across a family of initial states. Finally, we give a fixed game with a unique, strictly complementary equilibrium on which optimistic matrix multiplicative weights updates (OMMWU) converge only polynomially from the maximally mixed state for every fixed positive step size. The last-iterate Frobenius distance and quantum relative entropy from the equilibrium to the iterates decay as $Θ(1/t)$, while the duality gap decays as $Θ(1/t^2)$.

quant-ph↗

arXiv2026

Sparks of Cooperative Reasoning: LLMs as Strategic Hanabi Agents

Cooperative reasoning under incomplete information remains challenging for both humans and multi-agent systems. The card game Hanabi embodies this challenge, requiring theory-of-mind reasoning and strategic communication. We benchmark 17 state-of-the-art LLM agents in 2-5 player games and study the impact of context engineering across model scales (4B to 600B+) to understand persistent coordination failures and robustness to scaffolding: from a minimal prompt with only explicit card details (Watson setting), to scaffolding with programmatic, Bayesian-motivated deductions (Sherlock), to multi-turn state tracking via working memory (Mycroft setting). We show that (1) agents can maintain an internal working memory for state tracking and (2) cross-play performance between different LLMs smoothly interpolates with model strength. In the Sherlock setting, the strongest reasoning models exceed 15 points on average across player counts, yet still trail experienced humans and specialist Hanabi agents, both consistently scoring above 20. We release the first public Hanabi datasets with annotated trajectories and move utilities: (1) HanabiLogs, containing 1,520 full game logs for instruction tuning, and (2) HanabiRewards, containing 560 games with dense move-level value annotations for all candidate moves. Supervised and RL finetuning of a 4B open-weight model (Qwen3-Instruct) on our datasets improves cooperative Hanabi play by 21% and 156% respectively, bringing performance to within ~3 points of a strong proprietary reasoning model (o4-mini) and surpassing the best non-reasoning model (GPT-4.1) by 52%. The HanabiRewards RL-finetuned model further generalizes beyond Hanabi, improving performance on a cooperative group-guessing benchmark by 11%, temporal reasoning on EventQA by 6.4 points, instruction-following on IFBench by 1.7 Pass@10, and matching AIME 2025 mathematical reasoning Pass@10.

cs.CL↗

arXiv2026

Learning Safely Without Knowing the World:COMPASS-Hedge

Online learning algorithms often face a fundamental trilemma: balancing regret guarantees between adversarial and stochastic settings and providing baseline safety against a fixed comparator. While existing methods excel in one or two of these regimes, they typically fail to unify all three without sacrificing optimal rates or requiring oracle access to problem-dependent parameters. In this work, we bridge this gap by introducing COMPASS-Hedge. To the best of our knowledge, our algorithm is the first full-information anytime method to simultaneously achieve, up to logarithmic factors: i) minimax-optimal regret in adversarial environments; ii) instance-optimal, gap-dependent regret in stochastic environments; and iii) $\tilde{\mathcal{O}}(1)$ regret relative to a designated baseline policy. Crucially, COMPASS-Hedge is parameter-free and requires no prior knowledge of the environment's nature or the magnitude of the stochastic suboptimality gaps. Our approach hinges on a novel integration of adaptive pseudo-regret scaling and phase-based aggression, coupled with a comparator-aware mixing strategy. To the best of our knowledge, this provides the first "best-of-three-world" guarantee in the full-information setting, establishing that baseline safety does not have to come at the cost of worst-case robustness or stochastic efficiency.

cs.LG↗

arXiv2026

Prudent-Banker: No Extra Fees for Baseline Safety in Adversarial Bandits With and Without Delays

We study adversarial multi-armed bandits with and without delayed feedback under a safety-aware goal: achieving minimax-optimal worst-case regret while keeping nearly constant regret relative to a designated "safe" baseline policy. Existing approaches can balance this trade-off with immediate feedback for smooth comparators, but arbitrary delays can mistime transitions between conservatism and exploration, endangering the safety guarantee. To bridge this gap, we propose Prudent-Banker, a novel algorithm that combines a delay-adapted variant of Online Mirror Descent with a modified phased-aggression mechanism. Its key technical contribution is a delay-calibrated restart threshold that rigorously accounts for the worst-case distortion induced by unobserved feedback and reliably detects comparator suboptimality. We also establish new lower bounds for safety-constrained adversarial delayed bandits, showing that the regret guarantees of Prudent-Banker are unimprovable, up to logarithmic factors, under the baseline-safety requirement. To the best of our knowledge, Prudent-Banker is the first algorithm to achieve the optimal safety--robustness trade-off: pseudo-regret $\widetilde{O}(\sqrt{T}+\sqrt{D})$ together with $\widetilde{O}(1)$ regret against the safe comparator, both with and without delays. Experiments across diverse delay distributions show that, unlike standard delay-robust baselines, Prudent-Banker effectively balances safety and learning.

cs.LG↗

arXiv2026

No Coin Left Behind: Maximizing Strategic Surplus Against No-Regret Dynamics

We investigate the strategic surplus obtainable against a Follow-the-Regularized-Leader (FTRL) learner with constant step size $η$ in $n\times m$ two-player zero-sum games played over $T$ rounds against a clairvoyant optimizer. In contrast with prior analysis, we show that the extraction of such regret-scale surplus is an inherent feature of the FTRL family, rather than an artifact of specific instantiations. First, for a fixed max-min optimizer, we establish a sweeping law of order $Ω(N_{\mathrm{sub}}/η)$, proving that utility surplus scales with the number of the learner's suboptimal actions $N$ and vanishes in their absence. Second, for an alternating optimizer, a surplus of $Ω(ηT/\mathrm{poly}(n,m))$ can be guaranteed regardless of the equilibrium structure, with high probability, in random games. Our analysis uncovers a sharp geometric dichotomy: non-steep regularizers allow the optimizer to realize the maximal transient surplus via finite-time elimination of suboptimal actions, whereas steep regularizers introduce a vanishing tail correction that can delay surplus saturation. Finally, we discuss whether this leverage persists under bilateral payoff uncertainty and propose a susceptibility measure quantifying which regularizers are most vulnerable to learner-aware strategic steering.

cs.GT↗

arXiv2026

Shuffling the Data, Stretching the Step-size: Sharper Bias in constant step-size SGD

From adversarial robustness to multi-agent learning, many machine learning tasks can be cast as finite-sum min-max optimization or, more generally, as variational inequality problems (VIPs). Owing to their simplicity and scalability, stochastic gradient methods with constant step size are widely used, despite the fact that they converge only up to a constant term. Among the many heuristics adopted in practice, two classical techniques have recently attracted attention to mitigate this issue: \emph{Random Reshuffling} of data and \emph{Richardson--Romberg extrapolation} across iterates. Random Reshuffling sharpens the mean-squared error (MSE) of the estimated solution, while Richardson-Romberg extrapolation acts orthogonally, providing a second-order reduction in its bias. In this work, we show that their composition is strictly better than both, not only maintaining the enhanced MSE guarantees but also yielding an even greater cubic refinement in the bias. To the best of our knowledge, our work provides the first theoretical guarantees for such a synergy in structured non-monotone VIPs. Our analysis proceeds in two steps: (i) we smooth the discrete noise induced by reshuffling and leverage tools from continuous-state Markov chain theory to establish a novel law of large numbers and a central limit theorem for its iterates; and (ii) we employ spectral tensor techniques to prove that extrapolation debiases and sharpens the asymptotic behavior even under the biased gradient oracle induced by reshuffling. Finally, extensive experiments validate our theory, consistently demonstrating substantial speedups in practice.

math.OC↗

arXiv2025

Solving Neural Min-Max Games: The Role of Architecture, Initialization & Dynamics

Many emerging applications - such as adversarial training, AI alignment, and robust optimization - can be framed as zero-sum games between neural nets, with von Neumann-Nash equilibria (NE) capturing the desirable system behavior. While such games often involve non-convex non-concave objectives, empirical evidence shows that simple gradient methods frequently converge, suggesting a hidden geometric structure. In this paper, we provide a theoretical framework that explains this phenomenon through the lens of hidden convexity and overparameterization. We identify sufficient conditions - spanning initialization, training dynamics, and network width - that guarantee global convergence to a NE in a broad class of non-convex min-max games. To our knowledge, this is the first such result for games that involve two-layer neural networks. Technically, our approach is twofold: (a) we derive a novel path-length bound for the alternating gradient descent-ascent scheme in min-max games; and (b) we show that the reduction from a hidden convex-concave geometry to two-sided Polyak-Łojasiewicz (PŁ) min-max condition hold with high probability under overparameterization, using tools from random matrix theory.

cs.LG↗

arXiv2025

Last-Iterate Convergence of Adaptive Riemannian Gradient Descent for Equilibrium Computation

Equilibrium computation on Riemannian manifolds provides a unifying framework for numerous problems in machine learning and data analytics. One of the simplest yet most fundamental methods is Riemannian gradient descent (RGD). While its Euclidean counterpart has been extensively studied, it remains unclear how the manifold curvature affects RGD in game-theoretic settings. This paper addresses this gap by establishing new convergence results for \textit{geodesic strongly monotone} games. Our key result shows that RGD attains last-iterate linear convergence in a \textit{geometry-agnostic} fashion, a key property for applications in machine learning. We extend this guarantee to stochastic and adaptive variants -- SRGD and FARGD -- and establish that: (i) the sample complexity of SRGD is geometry-agnostic and optimal with respect to noise; (ii) FARGD matches the convergence rate of its non-adaptive counterpart up to constant factors, while avoiding reliance on the condition number. Overall, this paper presents the first geometry-agnostic last-iterate convergence analysis for games beyond the Euclidean settings, underscoring the surprising power of RGD -- despite its simplicity -- in solving a wide spectrum of machine learning problems.

math.OC↗

arXiv2025

Algorithms and Complexity for Computing Nash Equilibria in Adversarial Team Games

Adversarial team games model multiplayer strategic interactions in which a team of identically-interested players is competing against an adversarial player in a zero-sum game. Such games capture many well-studied settings in game theory, such as congestion games, but go well-beyond to environments wherein the cooperation of one team -- in the absence of explicit communication -- is obstructed by competing entities; the latter setting remains poorly understood despite its numerous applications. Since the seminal work of Von Stengel and Koller (GEB `97), different solution concepts have received attention from an algorithmic standpoint. Yet, the complexity of the standard Nash equilibrium has remained open. In this paper, we settle this question by showing that computing a Nash equilibrium in adversarial team games belongs to the class continuous local search (CLS), thereby establishing CLS-completeness by virtue of the recent CLS-hardness result of Rubinstein and Babichenko (STOC `21) in potential games. To do so, we leverage linear programming duality to prove that any $ε$-approximate stationary strategy for the team can be extended in polynomial time to an $O(ε)$-approximate Nash equilibrium, where the $O(\cdot)$ notation suppresses polynomial factors in the description of the game. As a consequence, we show that the Moreau envelop of a suitable best response function acts as a potential under certain natural gradient-based dynamics.

cs.GT↗

arXiv2025

Solving Zero-Sum Convex Markov Games

We contribute the first provable guarantees of global convergence to Nash equilibria (NE) in two-player zero-sum convex Markov games (cMGs) by using independent policy gradient methods. Convex Markov games, recently defined by Gemp et al. (2024), extend Markov decision processes to multi-agent settings with preferences that are convex over occupancy measures, offering a broad framework for modeling generic strategic interactions. However, even the fundamental min-max case of cMGs presents significant challenges, including inherent nonconvexity, the absence of Bellman consistency, and the complexity of the infinite horizon. We follow a two-step approach. First, leveraging properties of hidden-convex--hidden-concave functions, we show that a simple nonconvex regularization transforms the min-max optimization problem into a nonconvex-proximal Polyak-Lojasiewicz (NC-pPL) objective. Crucially, this regularization can stabilize the iterates of independent policy gradient methods and ultimately lead them to converge to equilibria. Second, building on this reduction, we address the general constrained min-max problems under NC-pPL and two-sided pPL conditions, providing the first global convergence guarantees for stochastic nested and alternating gradient descent-ascent methods, which we believe may be of independent interest.

cs.GT↗

arXiv2025

A Quadratic Speedup in Finding Nash Equilibria of Quantum Zero-Sum Games

Recent developments in domains such as non-local games, quantum interactive proofs, and quantum generative adversarial networks have renewed interest in quantum game theory and, specifically, quantum zero-sum games. Central to classical game theory is the efficient algorithmic computation of Nash equilibria, which represent optimal strategies for both players. In 2008, Jain and Watrous proposed the first classical algorithm for computing equilibria in quantum zero-sum games using the Matrix Multiplicative Weight Updates (MMWU) method to achieve a convergence rate of $\mathcal{O}(d/ε^2)$ iterations to $ε$-Nash equilibria in the $4^d$-dimensional spectraplex. In this work, we propose a hierarchy of quantum optimization algorithms that generalize MMWU via an extra-gradient mechanism. Notably, within this proposed hierarchy, we introduce the Optimistic Matrix Multiplicative Weights Update (OMMWU) algorithm and establish its average-iterate convergence complexity as $\mathcal{O}(d/ε)$ iterations to $ε$-Nash equilibria. This quadratic speed-up relative to Jain and Watrous' original algorithm sets a new benchmark for computing $ε$-Nash equilibria in quantum zero-sum games.

quant-ph↗

arXiv2025

Armada: Memory-Efficient Distributed Training of Large-Scale Graph Neural Networks

We study distributed training of Graph Neural Networks (GNNs) on billion-scale graphs that are partitioned across machines. Efficient training in this setting relies on min-edge-cut partitioning algorithms, which minimize cross-machine communication due to GNN neighborhood sampling. Yet, min-edge-cut partitioning over large graphs remains a challenge: State-of-the-art (SoTA) offline methods (e.g., METIS) are effective, but they require orders of magnitude more memory and runtime than GNN training itself, while computationally efficient algorithms (e.g., streaming greedy approaches) suffer from increased edge cuts. Thus, in this work we introduce Armada, a new end-to-end system for distributed GNN training whose key contribution is GREM, a novel min-edge-cut partitioning algorithm that can efficiently scale to large graphs. GREM builds on streaming greedy approaches with one key addition: prior vertex assignments are continuously refined during streaming, rather than frozen after an initial greedy selection. Our theoretical analysis and experimental results show that this refinement is critical to minimizing edge cuts and enables GREM to reach partition quality comparable to METIS but with 8-65x less memory and 8-46x faster. Given a partitioned graph, Armada leverages a new disaggregated architecture for distributed GNN training to further improve efficiency; we find that on common cloud machines, even with zero communication, GNN neighborhood sampling and feature loading bottleneck training. Disaggregation allows Armada to independently allocate resources for these operations and ensure that expensive GPUs remain saturated with computation. We evaluate Armada against SoTA systems for distributed GNN training and find that the disaggregated architecture leads to runtime improvements up to 4.5x and cost reductions up to 3.1x.

cs.LG↗

arXiv2024

Contracting with a Learning Agent

Many real-life contractual relations differ completely from the clean, static model at the heart of principal-agent theory. Typically, they involve repeated strategic interactions of the principal and agent, taking place under uncertainty and over time. While appealing in theory, players seldom use complex dynamic strategies in practice, often preferring to circumvent complexity and approach uncertainty through learning. We initiate the study of repeated contracts with a learning agent, focusing on agents who achieve no-regret outcomes. Optimizing against a no-regret agent is a known open problem in general games; we achieve an optimal solution to this problem for a canonical contract setting, in which the agent's choice among multiple actions leads to success/failure. The solution has a surprisingly simple structure: for some $α> 0$, initially offer the agent a linear contract with scalar $α$, then switch to offering a linear contract with scalar $0$. This switch causes the agent to ``free-fall'' through their action space and during this time provides the principal with non-zero reward at zero cost. Despite apparent exploitation of the agent, this dynamic contract can leave \emph{both} players better off compared to the best static contract. Our results generalize beyond success/failure, to arbitrary non-linear contracts which the principal rescales dynamically. Finally, we quantify the dependence of our results on knowledge of the time horizon, and are the first to address this consideration in the study of strategizing against learning agents.

cs.GT↗

arXiv2023

Exploiting hidden structures in non-convex games for convergence to Nash equilibrium

A wide array of modern machine learning applications - from adversarial models to multi-agent reinforcement learning - can be formulated as non-cooperative games whose Nash equilibria represent the system's desired operational states. Despite having a highly non-convex loss landscape, many cases of interest possess a latent convex structure that could potentially be leveraged to yield convergence to equilibrium. Driven by this observation, our paper proposes a flexible first-order method that successfully exploits such "hidden structures" and achieves convergence under minimal assumptions for the transformation connecting the players' control variables to the game's latent, convex-structured layer. The proposed method - which we call preconditioned hidden gradient descent (PHGD) - hinges on a judiciously chosen gradient preconditioning scheme related to natural gradient methods. Importantly, we make no separability assumptions for the game's hidden structure, and we provide explicit convergence rate guarantees for both deterministic and stochastic environments.

cs.GT↗

arXiv2023

Stochastic Methods in Variational Inequalities: Ergodicity, Bias and Refinements

For min-max optimization and variational inequalities problems (VIP) encountered in diverse machine learning tasks, Stochastic Extragradient (SEG) and Stochastic Gradient Descent Ascent (SGDA) have emerged as preeminent algorithms. Constant step-size variants of SEG/SGDA have gained popularity, with appealing benefits such as easy tuning and rapid forgiveness of initial conditions, but their convergence behaviors are more complicated even in rudimentary bilinear models. Our work endeavors to elucidate and quantify the probabilistic structures intrinsic to these algorithms. By recasting the constant step-size SEG/SGDA as time-homogeneous Markov Chains, we establish a first-of-its-kind Law of Large Numbers and a Central Limit Theorem, demonstrating that the average iterate is asymptotically normal with a unique invariant distribution for an extensive range of monotone and non-monotone VIPs. Specializing to convex-concave min-max optimization, we characterize the relationship between the step-size and the induced bias with respect to the Von-Neumann's value. Finally, we establish that Richardson-Romberg extrapolation can improve proximity of the average iterate to the global solution for VIPs. Our probabilistic analysis, underpinned by experiments corroborating our theoretical discoveries, harnesses techniques from optimization, Markov chains, and operator theory.

stat.ML↗

arXiv2023

Chaos persists in large-scale multi-agent learning despite adaptive learning rates

Multi-agent learning is intrinsically harder, more unstable and unpredictable than single agent optimization. For this reason, numerous specialized heuristics and techniques have been designed towards the goal of achieving convergence to equilibria in self-play. One such celebrated approach is the use of dynamically adaptive learning rates. Although such techniques are known to allow for improved convergence guarantees in small games, it has been much harder to analyze them in more relevant settings with large populations of agents. These settings are particularly hard as recent work has established that learning with fixed rates will become chaotic given large enough populations.In this work, we show that chaos persists in large population congestion games despite using adaptive learning rates even for the ubiquitous Multiplicative Weight Updates algorithm, even in the presence of only two strategies. At a technical level, due to the non-autonomous nature of the system, our approach goes beyond conventional period-three techniques Li-Yorke by studying fundamental properties of the dynamics including invariant sets, volume expansion and turbulent sets. We complement our theoretical insights with experiments showcasing that slight variations to system parameters lead to a wide variety of unpredictable behaviors.

cs.LG↗