A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
BGANs enable multi-agent learning with distributed private datasets.
We consider a simple model of a closed economic system where the total money is conserved and the number of economic agents is fixed. In analogy to statistical systems in equilibrium, money and the average money per economic agent are equivalent to energy and temperature, respectively. We investigate the effect of the …
Paper studies IPG method's robustness in noisy distributed linear regression.
We consider a financial market model which consists of a financial asset and a large number of interacting agents classified into many types. Different types of agents are heterogeneous in their price expectations. Each agent can change its type based on the current empirical distribution of the types and the equilibri…
Stochastic games provide a framework for interactions among multiple agents and enable a myriad of applications. In these games, agents decide on actions simultaneously, the state of every agent moves to the next state, and each agent receives a reward. However, finding an equilibrium (if exists) in this game is often …
The paper considers a class of multi-agent Markov decision processes (MDPs), in which the network agents respond differently (as manifested by the instantaneous one-stage random costs) to a global controlled state and the control actions of a remote controller. The paper investigates a distributed reinforcement learnin…
Paper addresses fault-tolerance in distributed machine learning with stochastic gradient descent.
A method to minimize regret in multi-agent control systems with adversarial disturbances.
Agents cooperate to make decisions in multi-armed bandits over a graph.
UD-SGD analysis shows efficient sampling by a few agents can outperform others.
New method speeds up distributed linear regression.
Pareto law, which states that wealth distribution in societies have a power-law tail, has been a subject of intensive investigations in statistical physics community. Several models have been employed to explain this behavior. However, most of the agent based models assume the conservation of number of agents and wealt…
We analyze systems of agents sharing light-tailed risky claims issued by different financial objects. Assuming exponentially distributed claims, we obtain that both agents' and system's losses follow generalized exponential mixture distributions. We show that this leads to qualitatively different results on individual …
We consider a distributed learning setup where a network of agents sequentially access realizations of a set of random variables with unknown distributions. The network objective is to find a parametrized distribution that best describes their joint observations in the sense of the Kullback-Leibler divergence. Apart fr…
We analyze a conservative market model for the competition among economic agents in a close society. A minimum dynamics ensures that the poorest agent has a chance to improve its economic welfare. After a transient, the system self-organizes into a critical state where the wealth distribution have a minimum threshold, …
The paper proposes a new method to evaluate LLM agent responses using ECDF clustering.
New algorithm identifies near-optimal policies in adversarial distributed RL settings.
Study optimal investment decisions for diverse risk-tolerant agents.
Extends Optimal Transport to multiple agents, aiming for equitable and optimal distribution.
We consider the ideal-gas models of trading markets, where each agent is identified with a gas molecule and each trading as an elastic or money-conserving (two-body) collision. Unlike in the ideal gas, we introduce saving propensity of agents, such that each agent saves a fraction of its money and trades with t…
Some general features of kinetic multi-agent models are reviewed, with particular attention to the relation between the agent saving propensities and the form of the equilibrium wealth distribution. The effect of a finite cutoff of the saving propensity distribution on the corresponding wealth distribution is studied. …
Paper tackles Byzantine resilience in distributed multi-task learning.
This paper studies the trading volumes and wealth distribution of a novel agent-based model of an artificial financial market. In this model, heterogeneous agents, behaving according to the Von Neumann and Morgenstern utility theory, may mutually interact. A Tobin-like tax (TT) on successful investments and a flat tax …
In this paper, we propose a distributed off-policy actor critic method to solve multi-agent reinforcement learning problems. Specifically, we assume that all agents keep local estimates of the global optimal policy parameter and update their local value function estimates independently. Then, we introduce an additional…
New algorithm tackles multi-agent reinforcement learning issues.
New algorithm reduces individual regret and communication costs in cooperative bandits.
This paper considers the problem of Byzantine fault tolerance in distributed linear regression in a multi-agent system. However, the proposed algorithms are given for a more general class of distributed optimization problems, of which distributed linear regression is a special case. The system comprises of a server and…
New collaborative algorithm improves personalized mean estimation in online settings.
This paper considers a distributed reinforcement learning problem in which a network of multiple agents aim to cooperatively maximize the globally averaged return through communication with only local neighbors. A randomized communication-efficient multi-agent actor-critic algorithm is proposed for possibly unidirectio…
The paper proves convergence to global optima for a class of distributed algorithms for nonconvex optimization in network-based multi-agent settings. Agents are permitted to communicate over a time-varying undirected graph. Each agent is assumed to possess a local objective function (assumed to be smooth, but possibly …
DEOT method compares distributions across agents with privacy and efficiency.
Paper proposes a pre-conditioning method to speed up gradient descent in multi-agent optimization.
In this article, we established a stock market model based on agents' investing mentality. The agents decide whether to purchase the shares at the probability, according to their anticipation of the market's behaviors. The expectation of the amount of shares they want to buy is directly proportional to the value of ass…
We consider the ideal-gas models of trading markets, where each agent is identified with a gas molecule and each trading as an elastic or money-conserving (two-body) collision. Unlike in the ideal gas, we introduce saving propensity of agents, such that each agent saves a fraction of its money and trades with t…
Robust reinforcement learning agents generalize well to out-of-distribution settings using pretrained representations.
We model a closed economic system with interactions that generates the features of empirical wealth distribution across all wealth brackets, namely a Gibbsian trend in the lower and middle wealth range and a Pareto trend in the higher range, by simply limiting the an agents' interaction to only agents with nearly the s…
Locally private reinforcement learning protects individual environments from reverse engineering.
Gaussian prior and likelihood improve bandit learning performance.
A deep RL framework optimizes resource allocation in wireless networks.
Distributed Quantum Gaussian Processes improve modeling in multi-agent systems.
We study the model of interacting agents proposed by Chatterjee et al that allows agents to both save and exchange wealth. Closed equations for the wealth distribution are developed using a mean field approximation. We show that when all agents have the same fixed savings propensity, subject to certain well defined app…
Boltzmann-Gibbs distribution arises as the statistical equilibrium probability distribution of money among the agents of a closed economic system where random and undirected exchanges are allowed. When considering a model with uniform savings in the exchanges, the final distribution is close to the gamma family. In thi…
This work proposes ACTC for adaptive distributed learning under communication constraints.
We propose a model for equity trading in a population of agents where each agent acts to achieve his or her target stock-to-bond ratio, and, as a feedback mechanism, follows a market adaptive strategy. In this model only a fraction of agents participates in buying and selling stock during a trading period, while the re…
In this work we essentially reinterpreted the Sieczka-Hołyst (SH) model to make it more suited for description of real markets. For instance, this reinterpretation made it possible to consider agents as crafty. These agents encourage their neighbors to buy some stocks if agents have an opportunity to sell these stocks.…
Tax dynamics affects wealth distribution in a linearly growing socio-economic model.
This paper accelerates distributed convex optimization by mitigating ill-conditioning issues.
Algorithm reduces regret in distributed kernel bandits with shared randomness.