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.
The paper extends physics-based information maximization to complex bandit problems.
New bandit algorithm maximizes information gain.
Proposes a new method to enhance neural learning by maximizing information gain.
Maximizing margins leads to lossless compression of training data.
The paper analyzes generalization of noisy, iterative algorithms using maximal leakage.
Proposes a framework to maximize mutual information in VAE models for better latent code representation.
Kernel methods linked to feature subspaces and maximal correlation kernels.
Recently, crowdsourcing has emerged as an effective paradigm for human-powered large scale problem solving in various domains. However, task requester usually has a limited amount of budget, thus it is desirable to have a policy to wisely allocate the budget to achieve better quality. In this paper, we study the princi…
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…
MIC consistently estimates dependence in large datasets.
Investors pay for additional asset information based on utility maximization.
Solves utility maximization for delayed informed investors.
Greedy policy maximizes information in unknown linear systems.
Optimizes information acquisition to reduce estimation risk and maximize utility.
Learning disentangled representation from any unlabelled data is a non-trivial problem. In this paper we propose Information Maximising Autoencoder (InfoAE) where the encoder learns powerful disentangled representation through maximizing the mutual information between the representation and given information in an unsu…
Within the well-known framework of financial portfolio optimization, we analyze the existing relationships between the condition of arbitrage and the utility maximization in presence of \emph{insider information}. We assume that, since the initial time, the information flow is altered by adding the knowledge of an addi…
Study utility maximization with delayed information in continuous time Gaussian markets.
A novel method integrates feature and topology views for unsupervised graph representation learning.
Semi-supervised clustering aims to introduce prior knowledge in the decision process of a clustering algorithm. In this paper, we propose a novel semi-supervised clustering algorithm based on the information-maximization principle. The proposed method is an extension of a previous unsupervised information-maximization …
TIM maximizes mutual information for few-shot learning, outperforming state-of-the-art methods.
MINIMALIST maximizes mutual information for likelihood estimation from simulated data.
We review recent results about the maximal values of the Kullback-Leibler information divergence from statistical models defined by neural networks, including naive Bayes models, restricted Boltzmann machines, deep belief networks, and various classes of exponential families. We illustrate approaches to compute the max…
The paper proposes a method to learn structured representations from unlabeled data using mutual information maximization.
InfoOT improves data alignment by maximizing mutual information.
We consider a framework involving behavioral economics and machine learning. Rationally inattentive Bayesian agents make decisions based on their posterior distribution, utility function and information acquisition cost Renyi divergence which generalizes Shannon mutual information). By observing these decisions, how ca…
The paper tackles adversarial robustness by maximizing worst-case mutual information.
Variational autoencoders (VAEs) have ushered in a new era of unsupervised learning methods for complex distributions. Although these techniques are elegant in their approach, they are typically not useful for representation learning. In this work, we propose a simple yet powerful class of VAEs that simultaneously resul…
MIRO learns robust latent spaces by maximizing mutual information with future information.
SQFA learns features maximizing Fisher-Rao distance for better classification.
The paper examines utility maximization in markets with hidden Gaussian drift, finding restrictions on model parameters.
Stokes' theorem's boundary maximizes entropy.
Maximizes coding rate difference for robust, discriminative features.
We are working to develop automated intelligent agents, which can act and react as learning machines with minimal human intervention. To accomplish this, an intelligent agent is viewed as a question-asking machine, which is designed by coupling the processes of inference and inquiry to form a model-based learning unit.…
We present a two-stage approach for learning dictionaries for object classification tasks based on the principle of information maximization. The proposed method seeks a dictionary that is compact, discriminative, and generative. In the first stage, dictionary atoms are selected from an initial dictionary by maximizing…
Crowdsourced data used in machine learning services might carry sensitive information about attributes that users do not want to share. Various methods have been proposed to minimize the potential information leakage of sensitive attributes while maximizing the task accuracy. However, little is known about the theory b…
This paper concerns the recursive utility maximization problem under partial information. We first transform our problem under partial information into the one under full information. When the generator of the recursive utility is concave, we adopt the variational formulation of the recursive utility which leads to a s…
Feature selection is one of the most fundamental problems in machine learning. An extensive body of work on information-theoretic feature selection exists which is based on maximizing mutual information between subsets of features and class labels. Practical methods are forced to rely on approximations due to the diffi…
We describe Information Forests, an approach to classification that generalizes Random Forests by replacing the splitting criterion of non-leaf nodes from a discriminative one -- based on the entropy of the label distribution -- to a generative one -- based on maximizing the information divergence between the class-con…
A privacy-constrained information extraction problem is considered where for a pair of correlated discrete random variables governed by a given joint distribution, an agent observes and wants to convey to a potentially public user as much information about as possible without compromising the amount of …
AMI framework improves text generation by optimizing mutual information between source and target.
Study on maximizing submodular functions with limited updates, achieving tight bounds and poly-time algorithms.
A method to improve image synthesis diversity using mutual information.
Active inference minimizes expected free energy for optimal behavior.
One primary focus in multimodal feature extraction is to find the representations of individual modalities that are maximally correlated. As a well-known measure of dependence, the Hirschfeld-Gebelein-Rényi (HGR) maximal correlation becomes an appealing objective because of its operational meaning and desirable propert…
Maximal correlation framework improves fairness in machine learning algorithms.
Graph Neural Networks (GNNs) achieve an impressive performance on structured graphs by recursively updating the representation vector of each node based on its neighbors, during which parameterized transformation matrices should be learned for the node feature updating. However, existing propagation schemes are far fro…
New active learning strategy improves decision-making accuracy.
New method corrects active learning for distribution shifts and outliers.