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.
Proposes a framework to maximize mutual information in VAE models for better latent code representation.
The paper proposes a method to learn structured representations from unlabeled data using mutual information maximization.
The paper tackles adversarial robustness by maximizing worst-case mutual information.
A novel method integrates feature and topology views for unsupervised graph representation learning.
MINIMALIST maximizes mutual information for likelihood estimation from simulated data.
Measuring mutual information from finite data is difficult. Recent work has considered variational methods maximizing a lower bound. In this paper, we prove that serious statistical limitations are inherent to any method of measuring mutual information. More specifically, we show that any distribution-free high-confide…
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…
AMI framework improves text generation by optimizing mutual information between source and target.
A method to improve image synthesis diversity using mutual information.
Proposes a framework to improve VAE latent codes using mutual information.
Reshef et al. recently proposed a new statistical measure, the "maximal information coefficient" (MIC), for quantifying arbitrary dependencies between pairs of stochastic quantities. MIC is based on mutual information, a fundamental quantity in information theory that is widely understood to serve this need. MIC, howev…
InfoOT improves data alignment by maximizing mutual information.
This paper proposes a method to learn graph representations without supervision.
MIRO learns robust latent spaces by maximizing mutual information with future information.
InfoMax-VAE enhances VAEs for better representation learning.
We describe a novel extension of soft actor-critics for hierarchical Deep Q-Networks (HDQN) architectures using mutual information metric. The proposed extension provides a suitable framework for encouraging explorations in such hierarchical networks. A natural utilization of this framework is an adversarial setting, w…
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 argue that the estimation of mutual information between high dimensional continuous random variables can be achieved by gradient descent over neural networks. We present a Mutual Information Neural Estimator (MINE) that is linearly scalable in dimensionality as well as in sample size, trainable through back-prop, an…
TIM maximizes mutual information for few-shot learning, outperforming state-of-the-art methods.
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…
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 …
InfoPrompt improves soft prompt tuning by maximizing mutual information, leading to better performance.
In this work, we develop a novel regularizer to improve the learning of long-range dependency of sequence data. Applied on language modelling, our regularizer expresses the inductive bias that sequence variables should have high mutual information even though the model might not see abundant observations for complex lo…
A variety of graph neural networks (GNNs) frameworks for representation learning on graphs have been recently developed. These frameworks rely on aggregation and iteration scheme to learn the representation of nodes. However, information between nodes is inevitably lost in the scheme during learning. In order to reduce…
A new method selects models for ensemble learning to maximize mutual information, outperforming existing approaches.
New method learns diverse solutions in reinforcement learning without gradient bias.
The paper analyzes generalization of noisy, iterative algorithms using maximal leakage.
Study on information evolution in interactive decision making using multi-armed bandits.
The paper introduces submodular information measures for machine learning applications.
Exploration is a difficult challenge in reinforcement learning and is of prime importance in sparse reward environments. However, many of the state of the art deep reinforcement learning algorithms, that rely on epsilon-greedy, fail on these environments. In such cases, empowerment can serve as an intrinsic reward sign…
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…
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…
We propose an approach to self-supervised representation learning based on maximizing mutual information between features extracted from multiple views of a shared context. For example, one could produce multiple views of a local spatio-temporal context by observing it from different locations (e.g., camera positions w…
This paper improves multi-class calibration methods using mutual information maximization-based binning.
In this paper, we investigate the problem of learning disentangled representations. Given a pair of images sharing some attributes, we aim to create a low-dimensional representation which is split into two parts: a shared representation that captures the common information between the images and an exclusive representa…
Mutual information maximization has emerged as a powerful learning objective for unsupervised representation learning obtaining state-of-the-art performance in applications such as object recognition, speech recognition, and reinforcement learning. However, such approaches are fundamentally limited since a tight lower …
New mutual information framework improves contrastive learning for vision tasks.
Standard accuracy metrics indicate that modern reading comprehension systems have achieved strong performance in many question answering datasets. However, the extent these systems truly understand language remains unknown, and existing systems are not good at distinguishing distractor sentences, which look related but…
Cross-entropy loss linked to metric learning, outperforming complex pairwise losses.
MSRL learns a representation maximizing mutual info with response variables.
New method improves DMs for solving inverse problems by maximizing conditional mutual information.
A novel algorithm for unsupervised graph representation learning combining coarsening and mutual information maximization.
We study the problem of supervised linear dimensionality reduction, taking an information-theoretic viewpoint. The linear projection matrix is designed by maximizing the mutual information between the projected signal and the class label (based on a Shannon entropy measure). By harnessing a recent theoretical result on…
Proposes a method to improve financial time series forecasting using compact representations and contrastive loss.
Optimal adversarial attacks minimize mutual information, revealing classifier vulnerabilities.
Spatio-temporal graphs such as traffic networks or gene regulatory systems present challenges for the existing deep learning methods due to the complexity of structural changes over time. To address these issues, we introduce Spatio-Temporal Deep Graph Infomax (STDGI)---a fully unsupervised node representation learning…
In this work, we perform unsupervised learning of representations by maximizing mutual information between an input and the output of a deep neural network encoder. Importantly, we show that structure matters: incorporating knowledge about locality of the input to the objective can greatly influence a representation's …
The goal of temporal alignment is to establish time correspondence between two sequences, which has many applications in a variety of areas such as speech processing, bioinformatics, computer vision, and computer graphics. In this paper, we propose a novel temporal alignment method called least-squares dynamic time war…