arXiv research

Unified framework extends adjoint Schrödinger bridge sampler to discrete spaces.

Adaptive discretization improves model-based RL in large spaces.

This study bridges discrete and continuous state spaces using the Ehrenfest process and diffusion models.

This primer explains diffusion models in general state spaces.

Study provides convergence guarantees for discrete diffusion models on finite and infinite state spaces.

CADD improves generative quality by augmenting discrete diffusion with continuous latent space.

A new model for time series using discrete latent states.

D2D-SPL uses discrete states and a classifier to train RL faster.

We present an efficient algorithm for model-free episodic reinforcement learning on large (potentially continuous) state-action spaces. Our algorithm is based on a novel $Q$-learning policy with adaptive data-driven discretization. The central idea is to maintain a finer partition of the state-action space in regions w…

Paper solves POMDPs in continuous time and discrete spaces.

NCDSSM models irregularly sampled time series with improved imputation and forecasting.

Deep neural network learns discrete state abstractions for efficient planning.

We give a Weierstrass type representation for semi-discrete minimal surfaces in Euclidean 3-space. We then give explicit parametrizations of various smooth, semi-discrete and fully-discrete catenoids, determined from either variational or integrable systems principles. Finally, we state the shared properties that those…

A new method reduces high-dimensional state space for dynamic choice models.

HiPPO-Prophecy models can learn dynamical systems without fine-tuning.

This paper analyzes discrete diffusion models, deriving convergence bounds for their generated samples.

DFMs enable flow-based models for multimodal discrete and continuous data.

Proposes DAM for optimizing discrete generative models.

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

EBMs trained on discrete data using heat equations on graph structures.

Study of filtering and smoothing in submanifolds of Euclidean space.

We describe discrete restricted Boltzmann machines: probabilistic graphical models with bipartite interactions between visible and hidden discrete variables. Examples are binary restricted Boltzmann machines and discrete naive Bayes models. We detail the inference functions and distributed representations arising in th…

Branching Flows generates sequences of varying lengths using binary trees.

The study proves a discrete version of Segre's theorem for polygonal curves.

Method infers causal structure from system behaviors using RKHS and kernel $ε$-machines.

We study Exo-MDPs to reduce sample complexity in reinforcement learning.

Discrete diffusion models improve data generation for discrete data like language and graphs.

New framework for discrete-state diffusion models reduces sample complexity.

A novel multi-resolution Gaussian process model for efficient time traversal.

Active inference is a process theory of the brain that states that all living organisms infer actions in order to minimize their (expected) free energy. However, current experiments are limited to predefined, often discrete, state spaces. In this paper we use recent advances in deep learning to learn the state space an…

Theory broadens GFlowNets to handle continuous spaces.

MDNS generates samples from complex discrete distributions efficiently.

GraphBSI generates graphs by refining a belief in continuous space, outperforming existing models.

GLAD improves latent graph generation by quantizing discrete latent space.

Paper introduces OMD for ordered state transitions in SSMs.

We investigate the statistical complexity of estimating the parameters of a discrete-state Markov chain kernel from a single long sequence of state observations. In the finite case, we characterize (modulo logarithmic factors) the minimax sample complexity of estimation with respect to the operator infinity norm, while…

Network slicing promises to provision diversified services with distinct requirements in one infrastructure. Deep reinforcement learning (e.g., deep $\mathcal{Q}$-learning, DQL) is assumed to be an appropriate algorithm to solve the demand-aware inter-slice resource management issue in network slicing by regarding the …

This paper improves MADDPG's performance in discrete grid-world scenarios.

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

ZoomRL learns efficient strategies for large state-action spaces using a metric.

There is a pressing need to build an architecture that could subsume these networks under a unified framework that achieves both higher performance and less overhead. To this end, two fundamental issues are yet to be addressed. The first one is how to implement the back propagation when neuronal activations are discret…

This paper deals with discrete-time Markov control processes on a general state space. A long-run risk-sensitive average cost criterion is used as a performance measure. The one-step cost function is nonnegative and possibly unbounded. Using the vanishing discount factor approach, the optimality inequality and an optim…

Corrected samplers reduce discretization error in discrete flow models without additional computational cost.

Proposes a new method for two-dimensional data discretization.

We consider a Hidden Markov Model (HMM) where the integrated continuous-time Markov chain can be observed at discrete time points perturbed by a Brownian motion. The aim is to derive a filter for the underlying continuous-time Markov chain. The recursion formula for the discrete-time filter is easy to derive, however i…

It is proved that every discrete Morse function in the sense of Forman on a finite regular CW complex can be represented by a polyhedral Morse function in the sense of Banchoff on an appropriate embedding in Euclidean space of the barycentric subdivision of the CW complex; such a representation preserves critical point…

Discrete noise improves graph generation quality and speed.

Learn true model from metastable samples of discrete distributions.