arXiv research

Investors suffer welfare loss despite having better information.

A new HRL method learns hierarchical policies using mutual information maximization.

RSVGD improves SVGD for Bayesian inference on Riemannian manifolds.

Many methods have been proposed for community detection in networks, but most of them do not take into account additional information on the nodes that is often available in practice. In this paper, we propose a new joint community detection criterion that uses both the network edge information and the node features to…

Optimizes trading co-integrated assets considering price impact and informational advantage.

UCB-Advantage learns MDPs with $O(\sqrt{H^2SAT})$ regret.

Paper proposes FedQ-Advantage for federated Q-learning with near-optimal regret and low communication cost.

Trading strategy advantage based on information asymmetry.

POSA optimizes policy gradients by reducing variance with RB and CV.

Information planning speeds up text data learning with fewer examples.

New algorithm optimizes exploration in unknown MDPs.

The paper characterizes information complexity for testing binary distributions in the broadcast model.

Improved SAC with AWMP for better control tasks.

Graph DNA uses Bloom filters to efficiently encode deep graph neighborhoods for better collaborative filtering.

InfoQGAN uses mutual information to improve QGANs, overcoming mode collapse and feature disentanglement issues.

Study linear contextual bandits with confounded offline data, improving regret bounds.

Gathering the most information by picking the least amount of data is a common task in experimental design or when exploring an unknown environment in reinforcement learning and robotics. A widely used measure for quantifying the information contained in some distribution of interest is its entropy. Greedily minimizing…

New method learns time-varying home field advantage in football.

New method estimates mutual information using normalizing flows.

New DDMs use neural networks for solving equations on manifold shapes.

Batch Active Learning uses derivative information for Gaussian Process regression.

New estimator improves mutual information estimation.

Successor Features improve transfer in RL by decoupling feature and reward.

NGD improves multivariate Gaussian inference by optimizing Fisher information.

Source separation problems are ubiquitous in the physical sciences; any situation where signals are superimposed calls for source separation to estimate the original signals. In this tutorial I will discuss the Bayesian approach to the source separation problem. This approach has a specific advantage in that it require…

Optimal stock portfolio strategy using information theory and Tsallis statistics.

Paper introduces DTAE to optimize RL algorithms, balancing exploration and exploitation.

Information-maximization clustering learns a probabilistic classifier in an unsupervised manner so that mutual information between feature vectors and cluster assignments is maximized. A notable advantage of this approach is that it only involves continuous optimization of model parameters, which is substantially easie…

Machine Learning benefits from prior information and computational power for better performance and understanding.

Enhances time-series modeling by dropping patches, improving efficiency and adaptability.

We propose and analyze estimators for statistical functionals of one or more distributions under nonparametric assumptions. Our estimators are based on the theory of influence functions, which appear in the semiparametric statistics literature. We show that estimators based either on data-splitting or a leave-one-out t…

New model shows big data isn't always better; some agents perform worse with more data.

In the information-based paradigm of inference, model selection is performed by selecting the candidate model with the best estimated predictive performance. The success of this approach depends on the accuracy of the estimate of the predictive complexity. In the large-sample-size limit of a regular model, the predicti…

Strategic brokers exploit private information in broker-mediated markets, affecting informed traders' performance.

SDPA is shown to be an optimal transport problem in deep learning.

IDS improves reinforcement learning with contextual information.

Paper introduces a core-periphery model for identifying informative network structures.

A fast feature selection method using OLS and SOCC for classification.

Extends information bottleneck to multi-view unsupervised learning.

Improved meta-learning for dynamics using additional structured knowledge.

A significant theoretical advantage of search-and-score methods for learning Bayesian Networks is that they can accept informative prior beliefs for each possible network, thus complementing the data. In this paper, a method is presented for assigning priors based on beliefs on the presence or absence of certain paths …

An asymmetric information model is introduced for the situation in which there is a small agent who is more susceptible to the flow of information in the market than the general market participant, and who tries to implement strategies based on the additional information. In this model market participants have access t…

FIA misleads in small samples; lower-bound sample size $N'$ prevents errors.

HSRL learns network embeddings capturing both local and global topology.

Paper introduces symmetric divergence link models for probability distributions.

Conditional meta-learning improves meta-learning performance in diverse task environments.

SCVAE mitigates degeneration in VAE by preserving information with skip connections.

New algorithm selects genes for cancer classification using adaptive elastic net and conditional mutual information.