The paper presents a method to estimate joint interventional distributions from marginal interventional data.
problem Estimating joint interventional distributions from marginal interventional data.
method The paper extends the Causal Maximum Entropy method to use interventional data and employs Lagrange duality to prove the solution lies in the exponential family.
result The method allows for causal feature selection and inference of joint interventional distributions.
A new IRL model recovers reward and state structure from expert demonstrations.
problem Limitation of classical maximum entropy model in capturing state structure.
method Generalized maximum causal entropy for IRL models.
result Empirically outperforms classical models in recovering reward and state structure.
New causal versions of MaxEnt and PIR avoid paradoxical probability updates.
problem Paradoxical probability updates in causal MaxEnt and PIR.
method Separate constraints into cause-specific and mechanism-specific restrictions.
result Causal MaxEnt avoids paradoxical updates and aligns with Information Geometric Causal Inference.
This work improves task specification learning from demonstrations using maximum causal entropy.
problem Lack of guarantees for safe task composition and historical dependencies in learning from demonstrations.
method Adapting maximum causal entropy inverse reinforcement learning to estimate task specifications using reduced ordered binary decision diagrams.
result Polynomial time algorithm for estimating task specifications from demonstrations.
In this paper, we propose a novel maximum causal Tsallis entropy (MCTE) framework for imitation learning which can efficiently learn a sparse multi-modal policy distribution from demonstrations. We provide the full mathematical analysis of the proposed framework. First, the optimal solution of an MCTE problem is shown …
New method uses entropy to generate multiple plausible causal maps.
problem Learning causal relationships from noisy data can lead to artifacts in DAGs.
method Entropy-based inference to generate an ensemble of plausible causal graphs.
result Multiple causal maps consistent with underlying data variability.
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.
New algorithm reduces performance loss in IRL with mismatched transition dynamics.
problem Performance degradation in inverse reinforcement learning due to mismatched transition dynamics.
method Proposed a robust Maximum Causal Entropy (MCE) IRL algorithm leveraging robust reinforcement learning insights.
result Empirically demonstrated stable performance improvement under transition dynamics mismatches.
Proposes PEID for analyzing synergistic causation in complex systems.
problem Challenges in identifying and analyzing synergistic causation in complex systems.
method Partial Effective Information Decomposition (PEID) framework.
result Unified and computable characterization of synergistic causal relations.
New method tightens bounds on causation probabilities using independent datasets.
problem Challenging point identification of causation probabilities without strong assumptions.
method Imposes counterfactual consistency between SCMs constructed from independent datasets and uses conditional mutual information.
result Significantly tighter bounds on causation probabilities are established.
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.
New measures for causal entropy and information gain studied.
problem Quantifying causal relationships in machine learning.
method Formal study of causal entropy and information gain.
result Established fundamental properties and relationships.
Multi-task Inverse Reinforcement Learning (IRL) is the problem of inferring multiple reward functions from expert demonstrations. Prior work, built on Bayesian IRL, is unable to scale to complex environments due to computational constraints. This paper contributes a formulation of multi-task IRL in the more computation…
The MAXENT principle helps merge datasets to infer causal effects.
problem Inferring causal effects from unobserved variables.
method Using the maximum entropy principle with causal sufficiency and faithfulness assumptions.
result Identifies causal edges among variables from merged datasets.
A new algorithm learns diverse policies in reinforcement learning.
problem Learning diverse behaviors in reinforcement learning.
method Proposes Maximum Entropy Diverse Exploration (MEDE) algorithm.
result The set of policies learned by MEDE capture the same modalities as the optimal maximum entropy policy.
Study on merging predictors in causal and anticausal directions using CMAXENT.
problem Comparing merging predictors in causal and anticausal directions.
method Using CMAXENT as inductive bias, study differences in merging predictors.
result CMAXENT solution reduces to logistic regression in causal direction and LDA in anticausal direction.
Paper proposes a method to estimate Transfer Entropy using Copula Entropy.
problem Estimating Transfer Entropy for causal discovery.
method Non-parametric method based on Copula Entropy.
result The proposed method effectively infers causality relationships from data.
Paper develops MRCs for supervised classification using generalized maximum entropy.
problem Developing robust classifiers for decision problems.
method Generalized maximum entropy principle applied to minimax risk classifiers.
result Learning techniques for determining MRCs with performance guarantees.
Develops variable-lag Granger causality and Transfer Entropy for time series analysis.
problem Fixed time delay assumption in Granger causality and Transfer Entropy does not hold in many applications.
method Variable-lag Granger causality and Transfer Entropy, using optimal warping path of Dynamic Time Warping (DTW).
result Proposed methods perform better than existing methods in both simulated and real-world datasets.
Paper proves causal direction can be inferred from data with limited randomness.
problem Inferring causal direction from observational data with limited randomness.
method Entropy measurement and structural causal models.
result Causal direction is identifiable for most causal models with limited entropy.
Maximum entropy modeling is a flexible and popular framework for formulating statistical models given partial knowledge. In this paper, rather than the traditional method of optimizing over the continuous density directly, we learn a smooth and invertible transformation that maps a simple distribution to the desired ma…
New algorithm improves causal effect estimation for continuous treatments.
problem Observational causal inference with continuous treatments.
method End-to-end entropy balancing for maximizing causal inference accuracy.
result Our algorithm estimates causal effect more accurately than baseline.
The well known maximum-entropy principle due to Jaynes, which states that given mean parameters, the maximum entropy distribution matching them is in an exponential family, has been very popular in machine learning due to its "Occam's razor" interpretation. Unfortunately, calculating the potentials in the maximum-entro…
We consider the problem of identifying the causal direction between two discrete random variables using observational data. Unlike previous work, we keep the most general functional model but make an assumption on the unobserved exogenous variable: Inspired by Occam's razor, we assume that the exogenous variable is sim…
Optimizes causal effects on unknown graphs using Causal Entropy Optimization.
problem Optimizing causal effects in unknown causal graphs.
method Causal Entropy Optimization (CEO) framework that generalizes Causal Bayesian Optimization (CBO). Incorporates causal structure uncertainty in surrogate models and intervention selection.
result CEO achieves faster convergence to global optimum compared to CBO and improves upon sequential structure learning.
Proposes efficient bounds for causal effect estimation under weak confounding.
problem Estimating causal effects with weakly confounded variables.
method Develops an efficient linear program to derive upper and lower bounds on causal effect under small entropy of unobserved confounders.
result Bounds are consistent and tighter for weakly confounded variables.
The study learns causal graphs from time series data using entropy measures.
problem Learning causal graphs from time series data.
method Constraint-based framework, information-theoretic measures, generalized causation entropy, PC and FCI algorithms.
result The methods effectively construct causal graphs from time series data.
MGD combines maximum entropy and diffusion methods for efficient sampling.
problem Generating samples from limited information in high dimensions.
method Moment Guided Diffusion (MGD) using stochastic differential equations.
result MGD efficiently samples maximum entropy distributions in finite time.
New causal measures improve feature selection in AI models.
problem Lack of causal interpretability in AI models.
method Introduces causal entropy and causal information gain to assess feature control.
result Demonstrates superiority of causal information gain in feature selection.
Researchers use Gaussian processes to approximate Lagrange multipliers for Maximum-Entropy distributions.
problem Finding Lagrange multipliers for Maximum-Entropy distributions is computationally challenging.
method Employed Gaussian processes to approximate the Lagrange multipliers as a map of moments. Optimized hyperparameters by maximizing log-likelihood.
result Data-driven Maximum-Entropy closure performs well in approximating non-equilibrium distributions.
This paper develops geometric tools for causal inference using information flow concepts.
problem Developing a geometric interpretation of causal inference from probabilistic measures.
method Introducing a new measure, GeoC_{y
ightarrow x}, based on fractal correlation dimension.
result Avoids boundedness issues in transfer entropy, providing a more robust measure of causal inference.
Enhances RL by controlling policy stochasticity through trajectory entropy constraints.
problem Non-stationary Q-value estimation and short-sighted entropy tuning in maximum entropy RL.
method Proposes TECRL framework with separate Q-functions for reward and entropy, enforcing a trajectory entropy constraint.
result DSAC-E algorithm achieves higher returns and better stability on OpenAI Gym benchmarks.
We present a new statistical learning paradigm for Boltzmann machines based on a new inference principle we have proposed: the latent maximum entropy principle (LME). LME is different both from Jaynes maximum entropy principle and from standard maximum likelihood estimation.We demonstrate the LME principle BY deriving …
This work presents entropic constraints from DAGs with hidden variables.
problem Characterizing causal relations in systems with hidden variables.
method Entropic inequality constraints derived from e-separation relations. result These constraints can learn about true causal models from observed data.
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…
We study the problem of discovering the simplest latent variable that can make two observed discrete variables conditionally independent. The minimum entropy required for such a latent is known as common entropy in information theory. We extend this notion to Renyi common entropy by minimizing the Renyi entropy of the …
We discuss the systemic risk implied by the interbank exposures reconstructed with the maximum entropy method. The maximum entropy method severely underestimates the risk of interbank contagion by assuming a fully connected network, while in reality the structure of the interbank network is sparsely connected. Here, we…
Bayesian models use hyperparameters to indirectly assign priors, and this work shows how these priors can be derived from maximum entropy principles.
problem Understanding the assumptions and dependencies in Bayesian hierarchical models.
method Demonstrates how canonical distributions and maximum entropy principles can be used to derive marginal priors in hierarchical models.
result Marginal priors in hierarchical models derived from maximum entropy principles have different constraints compared to the original priors.
Detects non-linear causality between social media sentiment and cryptocurrency prices.
problem Detecting causality between non-linear time series data.
method Use of transfer entropy to measure information transfer, validating against synthetic data, and applying significance tests.
result Significant non-linear causality detected, orders of magnitude greater than linear causality.
The maximum entropy principle can be used to assign utility values when only partial information is available about the decision maker's preferences. In order to obtain such utility values it is necessary to establish an analogy between probability and utility through the notion of a utility density function. According…
A novel framework infers causal direction from symbolic sequences using pattern entropy.
problem Challenges in discovering causal direction from temporal symbolic data.
method Dictionary Based Pattern Entropy (DPE) framework integrating AIT and Shannon Information Theory. result Minimizing pattern level uncertainty yields a robust framework for causal discovery.
The paper extends entropy maximization to multiscale settings and applies it to neural networks.
problem Achieving optimal risk bounds in neural networks using multiscale entropy.
method Generalizing maximum entropy to multiscale settings and applying it to neural networks.
result The multiscale Gibbs posterior can achieve a smaller excess risk than the single-scale Gibbs posterior in a teacher-student scenario.
Paper derives the maximum entropy characteristics of a rank order distribution for socio-economic applications.
problem Deriving the maximum entropy characteristics of a rank order distribution for socio-economic applications.
method Maximum entropy framework, deriving the discrete generalized beta distribution under a bivariate utility constraint.
result The discrete generalized beta distribution is a natural maximum entropy distribution under an appropriate bivariate utility constraint.
Improved exploration methods for reinforcement learning with reduced sample complexity.
problem Challenges in reinforcement learning exploration in unknown environments.
method Proposed game-theoretic and trajectory entropy algorithms with improved sample complexity.
result Established statistical advantage of entropy-regularized MDPs for exploration and reduced sample complexity.
IntDC framework uncovers causal relationships from non-interventional data.
problem Detecting causal relationships in non-interventional complex systems.
method Interventional Embedding Entropy (IEE) for causal strength measurement.
result IEE accurately finds causal edges and quantifies causal strength robustly.
Calculates local Granger causality for Gaussian and nonlinear systems.
problem Understanding causal influence in complex systems.
method Vector autoregression and information-theoretic approach.
result Local Granger causality offers a robust and fast method for time-directed information transfer.
Paper proposes a policy-search algorithm to learn entropy-maximizing exploration policies in reward-free environments.
problem Reward-free learning in high-dimensional, continuous-control domains.
method Maximum Entropy POLicy optimization (MEPOL) algorithm that maximizes a non-parametric state entropy estimate.
result MEPOL learns a maximum-entropy exploration policy that facilitates learning various reward-based tasks.
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.