arXiv research

New method uses neural exponential families for likelihood-free inference.

Study on parameter dynamics in exponential families under closed-loop learning.

A new method infers neural trajectories in real-time, improving experimental design.

We propose a Laplace approximation that creates a stochastic unit from any smooth monotonic activation function, using only Gaussian noise. This paper investigates the application of this stochastic approximation in training a family of Restricted Boltzmann Machines (RBM) that are closely linked to Bregman divergences.…

We describe \textit{deep exponential families} (DEFs), a class of latent variable models that are inspired by the hidden structures used in deep neural networks. DEFs capture a hierarchy of dependencies between latent variables, and are easily generalized to many settings through exponential families. We perform infere…

Neural operators solve families of 2BSDEs efficiently.

Word embeddings are a powerful approach for capturing semantic similarity among terms in a vocabulary. In this paper, we develop exponential family embeddings, a class of methods that extends the idea of word embeddings to other types of high-dimensional data. As examples, we studied neural data with real-valued observ…

Paper introduces kernel deformed exponential families for sparse continuous attention.

Paper interprets DNNs using RG for exponential family data.

Exponential family distributions are highly useful in machine learning since their calculation can be performed efficiently through natural parameters. The exponential family has recently been extended to the t-exponential family, which contains Student-t distributions as family members and thus allows us to handle noi…

In this paper we investigate the family of functions representable by deep neural networks (DNN) with rectified linear units (ReLU). We give an algorithm to train a ReLU DNN with one hidden layer to *global optimality* with runtime polynomial in the data size albeit exponential in the input dimension. Further, we impro…

The study explores generalized divergences and exponential families with a focus on sufficient conditions and laws of large numbers.

Generalizes moment-matching for exponential families with conditioning or hidden data.

Correspondence found between exponential families and affine Grassmannians.

We provide a classification of graphical models according to their representation as subfamilies of exponential families. Undirected graphical models with no hidden variables are linear exponential families (LEFs), directed acyclic graphical models and chain graphs with no hidden variables, including Bayesian networks …

Constructing exponential families from statistical manifolds.

Neuromorphic hardware platforms, such as Intel's Loihi chip, support the implementation of Spiking Neural Networks (SNNs) as an energy-efficient alternative to Artificial Neural Networks (ANNs). SNNs are networks of neurons with internal analogue dynamics that communicate by means of binary time series. In this work, a…

Thompson Sampling has been demonstrated in many complex bandit models, however the theoretical guarantees available for the parametric multi-armed bandit are still limited to the Bernoulli case. Here we extend them by proving asymptotic optimality of the algorithm using the Jeffreys prior for 1-dimensional exponential …

Moment polytope of toric exponential families is a projection of a simplex.

New Thompson sampling algorithm reduces regret for exponential family bandits.

We establish, for the first time, connections between feedforward neural networks with ReLU activation and tropical geometry --- we show that the family of such neural networks is equivalent to the family of tropical rational maps. Among other things, we deduce that feedforward ReLU neural networks with one hidden laye…

New tractable density models from squaring neural networks.

We study online learning under logarithmic loss with regular parametric models. Hedayati and Bartlett (2012b) showed that a Bayesian prediction strategy with Jeffreys prior and sequential normalized maximum likelihood (SNML) coincide and are optimal if and only if the latter is exchangeable, and if and only if the opti…

We propose a novel approach for density estimation with exponential families for the case when the true density may not fall within the chosen family. Our approach augments the sufficient statistics with features designed to accumulate probability mass in the neighborhood of the observed points, resulting in a non-para…

The versatility of exponential families, along with their attendant convexity properties, make them a popular and effective statistical model. A central issue is learning these models in high-dimensions, such as when there is some sparsity pattern of the optimal parameter. This work characterizes a certain strong conve…

New insights into natural exponential families improve regret bounds for bandit problems.

Deep equilibrium models estimate latent variables from data.

Paper explores robust estimators for kernel exponential families using smoothed total variation distances.

Extends likelihood ratio exponential families to analyze various optimization methods.

Efficient method for learning continuous exponential families beyond Gaussian.

Develops a new method for nonlinear dimension reduction using random features.

EFDA extends LDA to non-Gaussian models using exponential families.

New bounds for score matching in polynomial exponential families.

Exponential family extensions of principal component analysis (EPCA) have received a considerable amount of attention in recent years, demonstrating the growing need for basic modeling tools that do not assume the squared loss or Gaussian distribution. We extend the EPCA model toolbox by presenting the first exponentia…

New hyperbolic manifolds show exponential homology torsion growth.

Improves variational inference for sparse models using mixtures of exponential families.

SMRL uses score matching for efficient RL with exponential family models.

Neural network models improve survival analysis with reduced computation time.

CDEFs reduce model complexity and uncover time correlations.

NO approximates non-Markovian BSDEs with polynomial scaling in 1/ε.

We study the problem of finding the smallest $m$ such that every element of an exponential family can be written as a mixture of $m$ elements of another exponential family. We propose an approach based on coverings and packings of the face lattice of the corresponding convex support polytopes and results from coding th…

New method embeds bipartite graphs into vectors, overcoming nonlinear challenges.

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…

EFA extends self-attention to handle mixed data types and dynamic relevance.

We develop a general method for estimating a finite mixture of non-normalized models. Here, a non-normalized model is defined to be a parametric distribution with an intractable normalization constant. Existing methods for estimating non-normalized models without computing the normalization constant are not applicable …

This paper analyzes VAE approximation errors in conditional exponential families.

Novel simplex-valued distribution improves on existing models.

A new probabilistic mixup framework improves deep learning generalization.