arXiv research

DREAM learns optimal strategies in imperfect games without needing a simulator.

Optimal algorithm for two-player zero-sum games with linear parameterization.

Study efficient offline RL in Markov games with general models.

This paper improves sample efficiency for learning equilibria in multi-player games.

V-learning tackles multiagent reinforcement learning by reducing sample complexity.

New methods learn correlated equilibria in large games without structural assumptions.

Efficient reinforcement learning for simultaneous-move zero-sum games using optimistic value iteration.

Algorithm learns robust equilibrium in online Markov games with interactive data.

Paper develops efficient algorithms for learning rationalizable equilibria in multiplayer games.

Framework preserves emergent physics in non-equilibrium systems from particle trajectories.

CG-BGs combine flow-based models with PMFs to sample large systems efficiently.

New CGMD model predicts non-equilibrium processes better than existing methods.

Financial markets analyzed by reducing correlation matrix complexity.

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

DORIS algorithm achieves no-regret learning in Markov games with adversarial opponents.

Temporal aggregation reveals latent default correlation from monthly data.

The paper introduces Robust Correlated Equilibrium for games with time-varying costs and proposes an algorithm to achieve it.

Study insurance pricing under correlation ambiguity without increasing prices or reducing utility.

Paper solves learning imperfect-information games with fewer episodes.

The paper reduces the complexity of financial market correlation matrices to a 2x2 matrix.

Novel algorithms for multi-agent reinforcement learning reduce sample complexity.

Paper optimizes multi-agent learning in Markov games with generative model.

We introduce a quantitative approach to comparative statics that allows to bound the maximum effect of an exogenous parameter change on a system's equilibrium. The motivation for this approach is a well known paradox in multimarket Cournot competition, where a positive price shock on a monopoly market may actually redu…

We propose a data-driven, coarse-graining formulation in the context of equilibrium statistical mechanics. In contrast to existing techniques which are based on a fine-to-coarse map, we adopt the opposite strategy by prescribing a probabilistic coarse-to-fine map. This corresponds to a directed probabilistic model wher…

The notion of \emph{policy regret} in online learning is a well defined? performance measure for the common scenario of adaptive adversaries, which more traditional quantities such as external regret do not take into account. We revisit the notion of policy regret and first show that there are online learning settings …

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

Temporal coarse-graining of multi-sector default count data generates effective correlation matrices and rank copulas.

We introduce CSE for MLSF games and devise online learning algorithms for achieving no-external Stackelberg-regret.

MuSiCNet tackles irregularly sampled multivariate time series by treating them as a hierarchy of relatively regular series.

New algorithm improves sample efficiency for zero-sum Markov games.

We propose a new approach for analyzing price fluctuations in their strongly correlated regime ranging from minutes to months. This is done by employing a self-similarity assumption for the magnitude of coarse-grained price fluctuation or volatility. The existence of a Cramer function, the characteristic function for s…

Although there has been a rapid development of practical applications, theoretical explanations of deep learning are in their infancy. Deep learning performs a sophisticated coarse graining. Since coarse graining is a key ingredient of the renormalization group (RG), RG may provide a useful theoretical framework direct…

We consider a market model that consists of financial investors and producers of a commodity. Producers optionally store some production for future sale and go short on forward contracts to hedge the uncertainty of the future commodity price. Financial investors take positions in these contracts in order to diversify t…

Path-independent equilibrium models improve network performance on harder problems.

This paper introduces Schur-constant equilibrium distribution models of dimension n for arithmetic non-negative random variables. Such a model is defined through the (several orders) equilibrium distributions of a univariate survival function. First, the bivariate case is considered and analyzed in depth, stressing the…

Quantized deep neural networks (QDNNs) are attractive due to their much lower memory storage and faster inference speed than their regular full precision counterparts. To maintain the same performance level especially at low bit-widths, QDNNs must be retrained. Their training involves piecewise constant activation func…

New approach tackles non-stationary multi-agent games with black-box methods.

We study optimal behavior of energy producers under a CO_2 emission abatement program. We focus on a two-player discrete-time model where each producer is sequentially optimizing her emission and production schedules. The game-theoretic aspect is captured through a reduced-form price-impact model for the CO_2 allowance…

New method uses normalizing flows to improve force fields for coarse-grained molecular dynamics.

Models analyze strategic risk-taking in continuous action games.

Correlations and other collective phenomena in a schematic model of heterogeneous binary agents (individual spin-glass samples) are considered on the complete graph and also on 2d and 3d regular lattices. The system's stochastic dynamics is studied by numerical simulations. The dynamics is so slow that one can meaningf…

MLP residual networks implement a selective coarse-graining procedure governed by the spectral structure of the input distribution.

This paper tackles traffic volume estimation challenges with a deep learning method.

We propose a probabilistic model for refining coarse-grained spatial data by utilizing auxiliary spatial data sets. Existing methods require that the spatial granularities of the auxiliary data sets are the same as the desired granularity of target data. The proposed model can effectively make use of auxiliary data set…

We show that many machine learning goals, such as improved fairness metrics, can be expressed as constraints on the model's predictions, which we call rate constraints. We study the problem of training non-convex models subject to these rate constraints (or any non-convex and non-differentiable constraints). In the non…

We examine the correlation of the limit price with the order book, when a limit order comes. We analyzed the Rebuild Order Book of Stock Exchange Electronic Trading Service, which is the centralized order book market of London Stock Exchange. As a result, the limit price is broadly distributed around the best price acc…

The paper examines insurance market dynamics and optimal regulation.

Unified theory explains market impact using a simplified supply-demand parameter.