We extend common entropy concept and propose algorithms to distinguish causation from correlation.
problem Discovering the simplest latent variable for conditional independence of observed variables.
method Renyi common entropy, iterative algorithm, constraint-based methods modification.
result Improved constraint-based methods for causal inference in small samples.
This review explores entropy applications in data analysis and machine learning.
problem Characterizing probability mass distributions in data analysis and machine learning.
method Review of various entropy types and their applications.
result Entropy's versatility in data analysis and machine learning.
CEB enhances model resilience through simple entropy bottleneck.
problem Improving model robustness against adversarial attacks.
method Conditional Entropy Bottleneck (CEB) combined with data augmentation.
result CEB significantly boosts adversarial robustness on various benchmarks.
Study shows automorphisms of Markov surfaces share periodic points if they share a common iterate.
problem Study of unlikely intersections for automorphisms of Markov surfaces with positive entropy.
method Arithmetic equidistribution for adelic line bundles, theory of laminar currents, quasi-Fuchsian representation theory.
result Two automorphisms with positive entropy share a Zariski dense set of periodic points if and only if they share a common iterate.
New method identifies common cause in causal insufficiency, revealing complex phase transitions.
problem Identifying common cause in causal insufficiency with observed joint probability.
method Generalized maximum likelihood method, closely related to maximum entropy principle.
result Identifies consistent common cause that aligns with the common cause principle.
Entropy helps explain disorder in both macro and micro systems.
problem Connecting macro and micro systems with entropy analysis.
method Analyzing entropy from both macroscopic and microscopic perspectives.
result Entropy measures disorder in both macroscopic and microscopic systems.
Ancient curve shortening flows have entropy and curvature bounds equivalent.
problem Bounding entropy and total curvature for ancient curve shortening flows.
method Equivalence of entropy and total curvature conditions for ancient curve shortening flows.
result Entropy and total curvature bounds are equivalent for ancient curve shortening flows.
Study shows how market firm capitalization models converge to stochastic PDE solutions.
problem Understanding convergence of rank-based models with common noise to stochastic PDE solutions.
method Analysis of mean field limit, martingale problem, and pathwise entropy solutions.
result Empirical cumulative distribution function converges to solution of a stochastic PDE under certain conditions.
State entropy regularization improves robustness in reinforcement learning, especially under structured perturbations.
problem Structured and spatially correlated perturbations in reinforcement learning.
method State entropy regularization, compared to policy entropy.
result State entropy regularization provides better robustness to structured and spatially correlated perturbations.
Study on PG learning for LQ MFC problems with common noise, proving convergence and sample complexity.
problem Optimal policy learning in LQ MFC problems with common noise and entropy regularization.
method Comprehensive error analysis of PG algorithms in both model-based and model-free settings.
result Global linear convergence and sample complexity of PG algorithms in model-free setting.
Entropy rigidity theorem for cusped Hitchin representations.
problem Entropy rigidity for Hitchin representations of cusped groups.
method Introduction of (1,1,2)-hypertransverse groups and transverse representations.
result Hausdorff dimension of conical limit set agrees with simple root entropy.
This work improves policy optimization by maximizing entropy of state distribution, leading to better exploration.
problem Lack of exploration in state space when maximizing policy entropy.
method Proposes maximizing the entropy of a lower bound approximation to the state weighting distribution, based on latent space representation.
result Entropy regularization based on marginal state distribution achieves superior state space coverage and better performance in various domains.
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…
AER dynamically adjusts entropy regularization for better LLM reinforcement learning.
problem Policy entropy collapse in RLVR training limits exploration and reasoning performance.
method Adaptive Entropy Regularization (AER) with difficulty-aware coefficient allocation, initial-anchored target entropy, and dynamic global coefficient adjustment.
result AER consistently outperforms baselines on mathematical reasoning benchmarks, improving both accuracy and exploration.
Although both systems analyzed are described through two theories apparently different (quantum mechanics and game theory) it is shown that both are analogous and thus exactly equivalents. The quantum analogue of the replicator dynamics is the von Neumann equation. Quantum mechanics could be used to explain more correc…
Proposes HypCSE for enhanced hierarchical clustering.
problem Challenges in existing hierarchical clustering methods.
method Hyperbolic Continuous Structural Entropy (HypCSE) neural networks.
result Superior performance on seven datasets.
The so called "globalization" process (i.e. the inexorable integration of markets, currencies, nation-states, technologies and the intensification of consciousness of the world as a whole) has a behavior exactly equivalent to a system that is tending to a maximum entropy state. This globalization process obeys a collec…
Paper tests for time-varying entropy in stock prices, finding periods of inefficiency.
problem Testing for time-varying entropy in stock price dynamics.
method Unbiased approximation of Shannon entropy variance, optimal rolling window selection, hypothesis testing.
result Existence of periods of market inefficiency for meme stocks.
This paper provides efficient algorithms for computing entropy and KL divergence in Bayesian networks.
problem Computing entropy and KL divergence for Bayesian networks efficiently.
method Leveraging the graphical structure of Bayesian networks, the paper provides computationally efficient algorithms.
result Reduces computational complexity of KL divergence from cubic to quadratic for Gaussian BNs.
The need to estimate smooth probability distributions (a.k.a. probability densities) from finite sampled data is ubiquitous in science. Many approaches to this problem have been described, but none is yet regarded as providing a definitive solution. Maximum entropy estimation and Bayesian field theory are two such appr…
Examines predictability and complexity of economic time series using symbolic dynamics and entropy.
problem Understanding the predictability and complexity of economic time series.
method Symbolic dynamics and Information theory (entropy and uncertainty).
result Economic time series are complex and can be expressed in terms of information production.
Trust-region methods and natural gradients are equivalent in certain policy search scenarios.
problem Improving policy search methods in continuous control tasks.
method Introducing compatible policy search (COPOS) that uses natural parameterization and compatible value function approximation to control entropy loss.
result COPOS yields state-of-the-art results in challenging tasks and reduces entropy loss.
SimLoss improves classification by considering class similarities.
problem Equal punishment of all misclassifications in CCE.
method Integrates class similarities into Categorical Cross Entropy using matrices constructed from task-specific knowledge.
result Significant improvements over CCE on Age Estimation and Image Classification.
This paper examines the Histogram Loss for regression, revealing its effectiveness without needing complex tuning.
problem Improving regression models by learning the entire distribution.
method Investigates Histogram Loss, a method that minimizes cross-entropy between a target distribution and a histogram prediction.
result The performance gain in regression models using Histogram Loss comes from optimization improvements, not extra modeling.
We introduce a new algorithm, called CDER, for supervised machine learning that merges the multi-scale geometric properties of Cover Trees with the information-theoretic properties of entropy. CDER applies to a training set of labeled pointclouds embedded in a common Euclidean space. If typical pointclouds correspondin…
A new method for learning policies in multiple environments.
problem Learning policies that work in different but related environments.
method Decentralized entropy-regularized policy gradient method.
result The method can learn effective policies in multiple environments.
New method prevents entropy collapse in Transformer training, leading to more stable and robust models.
problem Training instability in Transformers, especially in attention layers.
method Spectral normalization with a learned scalar to prevent entropy collapse.
result Prevents entropy collapse, leading to more stable training.
Improved loss functions adapt to weight-space anisotropy, outperforming isotropic counterparts.
problem Adapting to the anisotropic nature of deep weight spaces for better performance.
method Refined local entropic loss functions restricted to a subset of weights, exploiting anisotropy.
result Partial local entropies outperform isotropic counterparts on image classification tasks.
New method tackles multi-task IRL in gridworlds with fewer demonstrations.
problem Inferring multiple reward functions from expert demonstrations in complex environments.
method Maximum Entropy IRL framework, leveraging meta-learning for function approximators.
result Approach solves multi-task IRL in gridworlds with fewer demonstrations than prior methods.
Proposes a cross entropy loss for better ranking algorithms.
problem Improving the theoretical understanding and performance of ranking algorithms.
method Introduces a cross entropy-based loss function that is a convex bound on NDCG and consistent with NDCG.
result Empirically, the proposed method outperforms existing algorithms in quality and robustness.
New method calibrates reference distributions for bounded support.
problem Lack of principled method for bounded-support statistical reference distributions.
method Formulated maximum entropy on projective space of nonnegative measures.
result Prescribed acceptance region uniquely determines deformation parameter.
Entropy-based model for hierarchical learning from multiscale data.
problem Learning from data with auxiliary information and multiscale target functions.
method Entropy-based hierarchical learning model with multiscale entropies.
result Entropy-based model yields stronger guarantees than uniform convergence bounds.
FedMAX tackles activation divergence in FL, improving accuracy and efficiency.
problem Activation divergence in Federated Learning due to non-IID data.
method Introduced a prior based on maximum entropy to minimize information about per-device activation vectors and make similar classes more alike.
result Significantly more similar activation vectors across multiple devices, leading to better accuracy and efficiency.
The paper clarifies that embeddings can either reduce or maintain the dimensionality of sparse feature spaces.
problem Misconception about embedding dimensionality in sparse feature spaces.
method Analysis of information entropy and upper bounds for embedding dimensions.
result Embeddings can either reduce or maintain the dimensionality of sparse feature spaces, providing a meaningful representation.
This paper improves test-time adaptation for distribution shifts using confidence maximization and input transformation.
problem Improving deep networks' performance on data shifted from the training distribution.
method Proposes a novel loss function combining confidence maximization and batch-wise entropy maximization with an input transformation module.
result Significantly improves robustness of pretrained networks to corruptions on benchmarks like ImageNet-C.
New algorithms improve neural network generalization by finding flat minima.
problem Finding better generalization in neural networks through flat minima.
method Developed Entropy-SGD and Replicated-SGD algorithms to maximize flatness in the loss function.
result Consistently improved generalization error for various deep learning architectures.
New scalable algorithm for non-negative linear regression with entropy-regularized OT loss.
problem Generalizing task-specific linear models to broader applications.
method Sinkhorn-like scaling iterations for convex penalty and datafit terms.
result Simple multiplicative updates for various penalty and datafit terms.
This work addresses two main issues of the standard Kernel Entropy Component Analysis (KECA) algorithm: the optimization of the kernel decomposition and the optimization of the Gaussian kernel parameter. KECA roughly reduces to a sorting of the importance of kernel eigenvectors by entropy instead of by variance as in K…
New method learns stochastic thermodynamics from system currents.
problem Understanding entropy production in complex dynamical systems.
method Constructs learning framework using currents and machine learning loss functions.
result Derives loss functions for thermodynamic functions directly from dynamics.
This work connects IRL methods from ML and economics.
problem Solving the inverse reinforcement learning problem.
method Shows connections and differences between various IRL methods.
result Identifies key computational and algorithmic differences.
Linear classifiers separate the data with a hyperplane. In this paper we focus on the novel method of construction of multithreshold linear classifier, which separates the data with multiple parallel hyperplanes. Proposed model is based on the information theory concepts -- namely Renyi's quadratic entropy and Cauchy-S…
One of the major issues studied in finance that has always intrigued, both scholars and practitioners, and to which no unified theory has yet been discovered, is the reason why prices move over time. Since there are several well-known traditional techniques in the literature to measure stock market volatility, a centra…
This paper proposes a new method for efficient data compression using Bayesian neural networks.
problem Efficient compression of data represented as functions mapping coordinates to signal values.
method Overfitting variational Bayesian neural networks to the data and compressing an approximate posterior weight sample using relative entropy coding.
result Our method achieves strong performance on image and audio compression while retaining simplicity.
Multifractal analysis is one of the important approaches that enables us to measure the complexity of various data via the scaling properties. We compare the most common techniques used for multifractal exponents estimation from both theoretical and practical point of view. Particularly, we discuss the methods based on…
Paper presents new matrix formats for deep neural networks that improve inference efficiency.
problem High computational cost of dot product operations in deep neural networks.
method Develops new matrix formats with bounded complexity by entropy of weight matrices.
result Up to x90 energy savings and x5 speed ups in dot product operations.
It is known that fixed points of loopy belief propagation (BP) correspond to stationary points of the Bethe variational problem, where we minimize the Bethe free energy subject to normalization and marginalization constraints. Unfortunately, this does not entirely explain BP because BP is a dual rather than primal algo…
Temperature scaling improves model uncertainty but not diversity in LLMs.
problem Improving the calibration and stochasticity of probabilistic models.
method Investigates theoretical properties of temperature scaling in classification and LLMs.
result Temperature scaling increases model uncertainty but not diversity in LLMs.
Optimizing full likelihoods adapts loss scales and shapes for robust modeling.
problem Rigid loss functions limit model adaptability and robustness.
method Optimize full likelihoods with adjustable parameters.
result Adaptive tuning of loss scales and shapes improves model robustness.