arXiv research

New games model strategic interactions in incomplete information settings.

Clusters of withdrawals emerge in banks due to latent fragility.

Study optimal policy regret in partially observable Markov games with adaptive opponents.

We study minority games in efficient regime. By incorporating the utility function and aggregating agents with similar strategies we develop an effective mesoscale notion of state of the game. Using this approach, the game can be represented as a Markov process with substantially reduced number of states with explicitl…

Paper tackles learning win-win solutions in aggregation systems.

pFedGame uses game theory for decentralized federated learning in dynamic networks.

Game theory models how agents trade in a risky asset considering price impact and a common signal.

Paper presents a novel approach for global feature aggregation in Graph Neural Networks.

Aggregates models from different datasets using shared latent structures.

GAME improves matrix completion by considering subgroup-specific latent structures.

A Nash game theory approach allocates capital requirements among financial institutions.

CARE improves LLM aggregation by accounting for shared confounders.

OpenAlpha validates decentralized capital strategies using game theory and market aggregation.

Federated learning linked to mean-field games for large-scale learning.

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…

Temporal aggregation reveals latent default correlation from monthly data.

The paper tackles targeted attacks on rank aggregation methods, proving the fixed point of adversarial game.

Research explores how interconnected systems synchronize and how to control their behavior.

Financial markets are often driven by latent factors which traders cannot observe. Here, we address an algorithmic trading problem with collections of heterogeneous agents who aim to perform optimal execution or statistical arbitrage, where all agents filter the latent states of the world, and their trading actions hav…

SCHA-VAE generates novel data from limited examples using hierarchical context aggregation.

New research shows no-regret learning is impossible in Markov games under certain assumptions.

We present a comprehensive study of utility function of the minority game in its efficient regime. We develop an effective description of state of the game. For the payoff function $g(x)=\sgn (x)$ we explicitly represent the game as the Markov process and prove the finitness of number of states. We also demonstrate bou…

Temporal coarse-graining of latent default paths explains effective correlation in corporate defaults.

This work improves multi-modal generative models by using permutation-invariant neural networks.

The article is devoted to investigating the application of aggregating algorithms to the problem of the long-term forecasting. We examine the classic aggregating algorithms based on the exponential reweighing. For the general Vovk's aggregating algorithm we provide its generalization for the long-term forecasting. For …

A variety of machine learning models have been proposed to assess the performance of players in professional sports. However, they have only a limited ability to model how player performance depends on the game context. This paper proposes a new approach to capturing game context: we apply Deep Reinforcement Learning (…

Method evaluates disentanglement in DLVMs, including those not aligned with latent axes.

A game-theoretic approach to multi-criteria ranking from ordinal data.

New approach models noisy labels without assuming a unique true label.

New game design method for better trait inference.

Deep learning enhances solving complex mean field games in finance.

We consider the dynamics of player's strategies in repeated market games, where the selection of strategies is determined by a learning model. Prior theoretical analysis and experimental data show that after large number of plays the average number of agents who decide to enter, per round of the game, approaches the ma…

GMVAEs cluster and generate game levels without labels.

Researchers analyze and improve latent space in NAR models.

Analyzes gaming in federated learning systems and provides design principles.

A method to train multi-agent reinforcement learning models without intrinsic rewards.

Mixability of a loss is known to characterise when constant regret bounds are achievable in games of prediction with expert advice through the use of Vovk's aggregating algorithm. We provide a new interpretation of mixability via convex analysis that highlights the role of the Kullback-Leibler divergence in its definit…

Maximizing product use is a central goal of many businesses, which makes retention and monetization two central analytics metrics in games. Player retention may refer to various duration variables quantifying product use: total playtime or session playtime are popular research targets, and active playtime is well-suite…

Study reveals RL game's embedding space is stratified, not a manifold.

Paper explores alternative cooperative game theory methods for machine learning feature attribution.

LPF provides formal guarantees for aggregating multi-evidence in probabilistic tasks.

Model explains periodic trading in financial markets through game theory.

Paper develops a new estimator for high-dimensional panel data with common shocks.

We present the Infinite Latent Events Model, a nonparametric hierarchical Bayesian distribution over infinite dimensional Dynamic Bayesian Networks with binary state representations and noisy-OR-like transitions. The distribution can be used to learn structure in discrete timeseries data by simultaneously inferring a s…

Two strategic agents track their portfolios, influencing each other's trading targets.

A new method assesses algorithmic fairness using game theory.

New method improves LLM judge accuracy by accounting for dependencies in aggregated binary labels.

A new method combines Gaussian graphical models for better distributed Gaussian process predictions.