arXiv research

MGD combines maximum entropy and diffusion methods for efficient sampling.

Improved exploration methods for reinforcement learning with reduced sample complexity.

MESSY estimation recovers symbolic density functions from samples using maximum entropy.

MEMEC improves sample efficiency in reinforcement learning.

A new method reduces compounding errors in model-based reinforcement learning.

New algorithm estimates semi-continuous data density using entropy maximization.

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…

Unified framework for network model assessment using maximum entropy.

This work extends ME-RL using diffusion models to sample optimal policies.

The paper solves a maximum entropy sampling problem with efficient algorithms and performance guarantees.

We discuss how maximum entropy methods may be applied to the reconstruction of Markov processes underlying empirical time series and compare this approach to usual frequency sampling. It is shown that, at least in low dimension, there exists a subset of the space of stochastic matrices for which the MaxEnt method is mo…

A new method speeds up quantum state estimation.

A new algorithm learns diverse policies in reinforcement learning.

Entropic herding generates smooth distributions for probabilistic modeling.

We study approximations of non-Gaussian stationary processes having long range correlations with microcanonical models. These models are conditioned by the empirical value of an energy vector, evaluated on a single realization. Asymptotic properties of maximum entropy microcanonical and macrocanonical processes and the…

Paper develops MRCs for supervised classification using generalized maximum entropy.

The paper tackles efficient exploration in MDPs to learn accurate models.

The application of standard sufficient dimension reduction methods for reducing the dimension space of predictors without losing regression information requires inverting the covariance matrix of the predictors. This has posed a number of challenges especially when analyzing high-dimensional data sets in which the numb…

Maximum entropy deep reinforcement learning (RL) methods have been demonstrated on a range of challenging continuous tasks. However, existing methods either suffer from severe instability when training on large off-policy data or cannot scale to tasks with very high state and action dimensionality such as 3D humanoid l…

A framework estimates categorical distributions under constraints, ensuring generality and uniqueness.

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…

MaxEnt Model Correction improves reinforcement learning model accuracy.

The ability of many powerful machine learning algorithms to deal with large data sets without compromise is often hampered by computationally expensive linear algebra tasks, of which calculating the log determinant is a canonical example. In this paper we demonstrate the optimality of Maximum Entropy methods in approxi…

The paper strengthens the classical result of MLE convergence to a Gaussian distribution.

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…

Researchers use Gaussian processes to approximate Lagrange multipliers for Maximum-Entropy distributions.

Enhances RL by controlling policy stochasticity through trajectory entropy constraints.

Maximum likelihood estimation of energy-based models is a challenging problem due to the intractability of the log-likelihood gradient. In this work, we propose learning both the energy function and an amortized approximate sampling mechanism using a neural generator network, which provides an efficient approximation o…

Quantum ML predicts data with improved speed and accuracy.

MIND estimates mutual information from ordinal data without full distributional knowledge.

The paper presents a method to estimate joint interventional distributions from marginal interventional data.

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 …

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…

DeepMaxent uses neural networks to improve species distribution models.

A new IRL model recovers reward and state structure from expert demonstrations.

Bayesian Entropy Neural Networks enforce constraints on deep learning predictions.

Entropy Search (ES) and Predictive Entropy Search (PES) are popular and empirically successful Bayesian Optimization techniques. Both rely on a compelling information-theoretic motivation, and maximize the information gained about the $\arg\max$ of the unknown function; yet, both are plagued by the expensive computatio…

Bayesian models use hyperparameters to indirectly assign priors, and this work shows how these priors can be derived from maximum entropy principles.

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…

The paper extends entropy maximization to multiscale settings and applies it to neural networks.

GACEM optimizes complex multi-modal problems using neural networks.

EntroPath learns manifold geometry from diffusion paths.

Paper proposes a policy-search algorithm to learn entropy-maximizing exploration policies in reward-free environments.

New method calibrates reference distributions for bounded support.

The paper introduces a new intrinsic reward method for exploration in reinforcement learning.

Max entropy exploration guides reinforcement learning agents to pursue achievable goals.

Synthesizes sensor likelihoods to enforce accuracy constraints in uncertain systems.

The problem of determining the joint probability distributions for correlated random variables with pre-specified marginals is considered. When the joint distribution satisfying all the required conditions is not unique, the "most unbiased" choice corresponds to the distribution of maximum entropy. The calculation of t…