arXiv research

Two EM algorithms estimate prior distributions in mixture of linear regressions.

Characterizes super-replication prices in a financial market model.

This research explores how different discrete diffusion kernels affect graph generation quality.

Paper formulates mutual information optimal control for discrete-time systems.

Training of discrete latent variable models remains challenging because passing gradient information through discrete units is difficult. We propose a new class of smoothing transformations based on a mixture of two overlapping distributions, and show that the proposed transformation can be used for training binary lat…

Boltzmann machines are powerful distributions that have been shown to be an effective prior over binary latent variables in variational autoencoders (VAEs). However, previous methods for training discrete VAEs have used the evidence lower bound and not the tighter importance-weighted bound. We propose two approaches fo…

A new method learns discrete representations for images and videos, improving upon previous models.

Boltzmann machines (BMs) are appealing candidates for powerful priors in variational autoencoders (VAEs), as they are capable of capturing nontrivial and multi-modal distributions over discrete variables. However, non-differentiability of the discrete units prohibits using the reparameterization trick, essential for lo…

A new model trains prior and encoder/decoder networks simultaneously for efficient generation.

Open problem: Establishing bounds for Cayley-table completion to discover discrete algorithmic axioms.

PRISM-VQ combines financial priors with vector quantization for better stock prediction.

Paper develops Bayesian inference for discrete-choice mnp models with Gaussian priors.

Unified framework for convergence of discrete diffusion models without state space size dependence.

In a discrete time and multiple-priors setting, we propose a new characterisation of the condition of quasi-sure no-arbitrage which has become a standard assumption. This characterisation shows that it is indeed a well-chosen condition being equivalent to several previously used alternative notions of no-arbitrage and …

We present a mixed multinomial logit (MNL) model, which leverages the truncated stick-breaking process representation of the Dirichlet process as a flexible nonparametric mixing distribution. The proposed model is a Dirichlet process mixture model and accommodates discrete representations of heterogeneity, like a laten…

In this paper, I present VQ-DRAW, an algorithm for learning compact discrete representations of data. VQ-DRAW leverages a vector quantization effect to adapt the sequential generation scheme of DRAW to discrete latent variables. I show that VQ-DRAW can effectively learn to compress images from a variety of common datas…

A new model tackles language generation issues by using discrete variational attention.

A new model predicts discrete events with flexible, nonparametric baseline and excitation.

Empirical Bayes rates via variational approximations and prior decomposition.

Recent neural text-to-speech (TTS) models with fine-grained latent features enable precise control of the prosody of synthesized speech. Such models typically incorporate a fine-grained variational autoencoder (VAE) structure, extracting latent features at each input token (e.g., phonemes). However, generating samples …

It has been widely understood that differential privacy (DP) can guarantee rigorous privacy against adversaries with arbitrary prior knowledge. However, recent studies demonstrate that this may not be true for correlated data, and indicate that three factors could influence privacy leakage: the data correlation pattern…

Plug-and-play L-GM-AMP improves CS recovery for any i.i.d. source prior.

Improved bounds for estimating discrete distributions in KL divergence.

Investor optimizes investment strategy under model uncertainty and random utility.

Bayesian Tensor Ring factorization improved for scalability and handling of discrete data.

A new model for time series using discrete latent states.

Extends Neural ODEs to model discrete changes in continuous systems.

New method learns disentangled discrete representations using categorical variational autoencoders.

This paper formulates an utility indifference pricing model for investors trading in a discrete time financial market under non-dominated model uncertainty. The investors preferences are described by strictly increasing concave random functions defined on the positive axis. We prove that under suitable conditions the m…

Meta-learning for discrete tasks using submodular optimization.

A new method for categorical variational inference using discrete normalizing flows.

Flow Annealing Posterior Sampling unifies stochastic-process regression and PDE inverse problems.

Representations based on random walks can exploit discrete data distributions for clustering and classification. We extend such representations from discrete to continuous distributions. Transition probabilities are now calculated using a diffusion equation with a diffusion coefficient that inversely depends on the dat…

FLOP algorithm speeds up causal structure learning for linear models.

We describe algorithms for learning Bayesian networks from a combination of user knowledge and statistical data. The algorithms have two components: a scoring metric and a search procedure. The scoring metric takes a network structure, statistical data, and a user's prior knowledge, and returns a score proportional to …

We consider the problem of estimating the transition rate matrix of a continuous-time Markov chain from a finite-duration realisation of this process. We approach this problem in an imprecise probabilistic framework, using a set of prior distributions on the unknown transition rate matrix. The resulting estimator is a …

We take prior-to-crash market prices (NASDAQ, Dow Jones Industrial Average) as a signal, a function of time, we project these discrete values onto a vertical axis, thus obtaining a Cantordust. We study said cantordust with the tools of multifractal analysis, obtaining spectra by definition and by lagrangian coordinates…

Proposes a non-parametric method for deep discrete latent variable models.

Low-rank matrix estimation from incomplete measurements recently received increased attention due to the emergence of several challenging applications, such as recommender systems; see in particular the famous Netflix challenge. While the behaviour of algorithms based on nuclear norm minimization is now well understood…

Investment strategy optimization from discrete to continuous models.

Improved sampling guarantees for underdamped Langevin Monte Carlo without restrictive assumptions.

In variational autoencoders, the prior on the latent codes $z$ is often treated as an afterthought, but the prior shapes the kind of latent representation that the model learns. If the goal is to learn a representation that is interpretable and useful, then the prior should reflect the ways in which the high-level fact…

Simplified analysis of diffusion models using discrete random variables.

BayesSum improves Bayesian quadrature for discrete domains, requiring fewer samples.

Bayesian network structure learning is often performed in a Bayesian setting, by evaluating candidate structures using their posterior probabilities for a given data set. Score-based algorithms then use those posterior probabilities as an objective function and return the maximum a posteriori network as the learned mod…

Discrete Morse theory emerged as an essential tool for computational geometry and topology. Its core structures are discrete gradient fields, defined as acyclic matchings on a complex $C$, from which topological and geometrical informations of $C$ can be efficiently computed, in particular its homology or Morse-Smale d…

SDE automatically recovers interpretable discrete distributions.

Exact Bayesian inference for discrete models using probability generating functions.