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.
New algorithm tackles multi-agent reinforcement learning issues.
Ogburn et al. (2019, arXiv:1910.05438) discuss "The Blessings of Multiple Causes" (Wang and Blei, 2018, arXiv:1805.06826). Many of their remarks are interesting. But they also claim that the paper has "foundational errors" and that its "premise is...incorrect." These claims are not substantiated. There are no foundatio…
High-dimensional data and high-dimensional representations of reality are inherent features of modern Artificial Intelligence systems and applications of machine learning. The well-known phenomenon of the "curse of dimensionality" states: many problems become exponentially difficult in high dimensions. Recently, the ot…
Federated Q-learning achieves linear speedup with heterogeneity, improving sample complexity.
This note has been updated (April, 2020) to respond to "Towards Clarifying the Theory of the Deconfounder" by Yixin Wang, David M. Blei (arXiv:2003.04948). This original note, posted in January, 2020, is meant to complement our previous comment on "The Blessings of Multiple Causes" by Wang and Blei (2019). We provide a…
Stacking improves inference for multimodal Bayesian posterior distributions.
This commentary has two goals. We first critically review the deconfounder method and point out its advantages and limitations. We then briefly consider three possible ways to address some of the limitations of the deconfounder method.
(This comment has been updated to respond to Wang and Blei's rejoinder [arXiv:1910.07320].) The premise of the deconfounder method proposed in "Blessings of Multiple Causes" by Wang and Blei [arXiv:1805.06826], namely that a variable that renders multiple causes conditionally independent also controls for unmeasured mu…
Unobserved confounding is a major hurdle for causal inference from observational data. Confounders---the variables that affect both the causes and the outcome---induce spurious non-causal correlations between the two. Wang & Blei (2018) lower this hurdle with "the blessings of multiple causes," where the correlation st…
Causal inference from observational data often assumes "ignorability," that all confounders are observed. This assumption is standard yet untestable. However, many scientific studies involve multiple causes, different variables whose effects are simultaneously of interest. We propose the deconfounder, an algorithm that…
Regularization can improve both privacy and performance in machine learning models.
New research shows CFG improves high-dimensional data generation.
Paper shows how noisy data can improve robust decision-making.
We review some statistical many-agent models of economic and social systems inspired by microscopic molecular models and discuss their stochastic interpretation. We apply these models to wealth exchange in economics and study how the relaxation process depends on the parameters of the system, in particular on the savin…
The interaction between transitivity and sparsity, two common features in empirical networks, implies that there are local regions of large sparse networks that are dense. We call this the blessing of transitivity and it has consequences for both modeling and inference. Extant research suggests that statistical inferen…
The aim of this comment (set to appear in a formal discussion in JASA) is to draw out some conclusions from an extended back-and-forth I have had with Wang and Blei regarding the deconfounder method proposed in "The Blessings of Multiple Causes" [arXiv:1805.06826]. I will make three points here. First, in my role as th…
Develops a framework for analyzing multi-agent and many-body systems with feedback loops.
High-dimensional models pose both safety benefits and risks.
The power of neural networks lies in their ability to generalize to unseen data, yet the underlying reasons for this phenomenon remain elusive. Numerous rigorous attempts have been made to explain generalization, but available bounds are still quite loose, and analysis does not always lead to true understanding. The go…
This paper tackles nonsmooth optimization in machine learning.
Many learning agents impact a financial market model, showing complex dynamics.
This paper examines how adversarial perturbations affect model performance and equilibrium learning.
Deep reinforcement learning (DRL) is a booming area of artificial intelligence. Many practical applications of DRL naturally involve more than one collaborative learners, making it important to study DRL in a multi-agent context. Previous research showed that effective learning in complex multi-agent systems demands fo…
Bayesian principles improve agentic AI decision-making.
MASA framework uses RL to balance portfolio returns and risks.
Improved multi-task averaging reduces mean squared error in high-dimensional data.
This paper will examine a model with many agents, each of whom has a different belief about the dynamics of a risky asset. The agents are Bayesian and so learn about the asset over time. All agents are assumed to have a finite (but random) lifetime. When an agent dies, he passes his wealth (but not his knowledge) onto …
Deep RL improves Diplomacy performance, outperforming previous methods.
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…
Adversaries can manipulate cooperative MARL networks.
New approach incentivizes strategic agents to explore, making exploration almost free.
The average economic agent is often used to model the dynamics of simple markets, based on the assumption that the dynamics of many agents can be averaged over in time and space. A popular idea that is based on this seemingly intuitive notion is to dampen electric power fluctuations from fluctuating sources (as e.g. wi…
Recent advances in artificial intelligence have been driven by the presence of increasingly realistic and complex simulated environments. However, many of the existing environments provide either unrealistic visuals, inaccurate physics, low task complexity, restricted agent perspective, or a limited capacity for intera…
BDDMs eliminate noise conditioning in diffusion models, simplifying training and sampling.
Agents learn to communicate and solve navigation tasks efficiently.
Study optimal portfolios for many players in a market model with random coefficients.
Safe-M-UCRL learns safe policies for multi-agent systems with global constraints.
The objective of the paper is to study accuracy of multi-class classification in high-dimensional setting, where the number of classes is also large ("large , large , small " model). While this problem arises in many practical applications and many techniques have been recently developed for its solution, to t…
We study a portfolio optimization problem for competitive agents with CRRA utilities and a common finite time horizon. The utility of an agent depends not only on her absolute wealth and consumption but also on her relative wealth and consumption when compared to the averages among the other agents. We derive a closed …
Many potential applications of reinforcement learning in the real world involve interacting with other agents whose numbers vary over time. We propose new neural policy architectures for these multi-agent problems. In contrast to other methods of training an individual, discrete policy for each agent and then enforcing…
Multi-agent models have been used in many contexts to study generic collective behavior. Similarly, complex networks have become very popular because of the diversity of growth rules giving rise to scale-free behavior. Here we study adaptive networks where the agents trade ``wealth'' when they are linked together while…
Reproducibility in reinforcement learning is challenging: uncontrolled stochasticity from many sources, such as the learning algorithm, the learned policy, and the environment itself have led researchers to report the performance of learned agents using aggregate metrics of performance over multiple random seeds for a …
Multi-agent systems exhibit complex behaviors that emanate from the interactions of multiple agents in a shared environment. In this work, we are interested in controlling one agent in a multi-agent system and successfully learn to interact with the other agents that have fixed policies. Modeling the behavior of other …
Many real world tasks require multiple agents to work together. Multi-agent reinforcement learning (RL) methods have been proposed in recent years to solve these tasks, but current methods often fail to efficiently learn policies. We thus investigate the presence of a common weakness in single-agent RL, namely value fu…
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…
Study many-player investment-consumption games with power FPPs, finding market-risk preference affects consumption.
Paper proves efficiency of MARL with transformers, addressing agent complexity.
In this paper we show that very large mixtures of Gaussians are efficiently learnable in high dimension. More precisely, we prove that a mixture with known identical covariance matrices whose number of components is a polynomial of any fixed degree in the dimension n is polynomially learnable as long as a certain non-d…