POWSS simplifies Q-value estimation in POMDPs with continuous observations.
problem Lack of theoretical justification for online sampling-based algorithms in POMDPs with continuous observation spaces.
method Developed POWSS, a simplified algorithm that estimates Q-values accurately with high probability and can approach optimality with increased computational power.
result POWSS provides formal theoretical guarantees for Q-value estimation in POMDPs with continuous observations.
New algorithm for aggregate inference in HMMs with continuous observations.
problem Inference in large populations with indistinguishable individuals and continuous measurements.
method Continuous observation collective forward-backward algorithm extending existing discrete case algorithm.
result Efficacy demonstrated through numerical experiments.
Paper solves POMDPs in continuous time and discrete spaces.
problem Optimal decision making in discrete state and action space systems under partial observability.
method Combining optimal filtering theory and deep learning to solve a Hamilton-Jacobi-Bellman equation.
result Derives a mathematical description and solution approach for continuous-time POMDPs.
NeuTSFlow models continuous functions behind time series forecasting.
problem Forecasting treats time series as discrete sequences, ignoring their continuous nature.
method NeuTSFlow uses Neural Operators to learn the transition between historical and future function families.
result NeuTSFlow outperforms traditional methods in forecasting accuracy and robustness.
RichID learns optimal control policies from nonlinear observations.
problem Continuous control with unknown nonlinearity in system model.
method RichID algorithm using a least-squares regression oracle.
result First provable sample complexity guarantee for continuous control.
Paper establishes baselines for offline RL from visual observations.
problem Challenges in offline reinforcement learning from visual observations with continuous action spaces.
method Simple baselines and benchmarking tasks for offline RL from visual observations.
result Simple modifications to existing online RL algorithms outperform existing offline RL methods.
In many fields observations are performed irregularly along time, due to either measurement limitations or lack of a constant immanent rate. While discrete-time Markov models (as Dynamic Bayesian Networks) introduce either inefficient computation or an information loss to reasoning about such processes, continuous-time…
Nonlocal Bayesian modeling for continuous spatio-temporal dynamics
problem Handling irregular time points, sparse observations, and nonlocal interactions in spatio-temporal forecasting
method Hierarchical Bayesian framework with coordinate-based spatial basis expansion and continuous-time ODE
result Strong forecasting and uncertainty calibration
NCDSSM models irregularly sampled time series with improved imputation and forecasting.
problem Accurate modeling of irregularly sampled time series with missing observations.
method Neural Continuous-Discrete State Space Model (NCDSSM) with amortized inference for auxiliary variables and flexible dynamic state parameterizations.
result Improved imputation and forecasting performance on multiple benchmark datasets.
Earth observation embeddings can convert discrete biome maps into continuous representations that better capture ecological variation.
problem Biome maps impose categorical boundaries that compress continuous variation in biotic communities.
method Fit a linear classifier on Earth observation embeddings to predict biome labels.
result Continuous biome representation outperforms discrete biome labels for predicting species occurrence.
Theory broadens GFlowNets to handle continuous spaces.
problem Limitation of GFlowNets to discrete spaces.
method Developed a theory for generalized GFlowNets.
result Empirical results show strong performance in continuous cases.
Graph neural networks learn PDEs from sparse, irregular data.
problem Learning PDEs from irregularly spaced data.
method Continuous-time differential model with graph neural networks for arbitrary discretizations.
result Efficient inference with continuous-time adjoint method.
High-dimensional always-changing environments constitute a hard challenge for current reinforcement learning techniques. Artificial agents, nowadays, are often trained off-line in very static and controlled conditions in simulation such that training observations can be thought as sampled i.i.d. from the entire observa…
Proposes VCNet for estimating ADRFs of continuous treatments.
problem Estimating ADRFs of continuous treatments from observational data.
method VCNet for improved model expressiveness and continuity; targeted regularization for finite sample performance.
result Improves model expressiveness and continuity of ADRFs.
New IRL algorithm for continuous state spaces with formal guarantees.
problem Finding a reward function for expert behavior in continuous state spaces.
method Modeling the system using orthonormal functions and providing correctness proofs.
result Proof of correctness and formal guarantees on sample and time complexity.
We consider the optimization of an uncertain objective over continuous and multi-dimensional decision spaces in problems in which we are only provided with observational data. We propose a novel algorithmic framework that is tractable, asymptotically consistent, and superior to comparable methods on example problems. O…
This study bridges discrete and continuous state spaces using the Ehrenfest process and diffusion models.
problem Understanding the relationship between discrete and continuous state spaces in stochastic processes.
method Investigates time-continuous Markov jump processes on discrete state spaces and their correspondence to state-continuous diffusion processes.
result The time-reversal of the Ehrenfest process converges to the time-reversed Ornstein-Uhlenbeck process, bridging discrete and continuous state spaces.
ACSSM models irregular time series with continuous dynamics.
problem Modeling irregular time series data.
method ACSSM uses a multi-marginal Doob's h-transform and variational inference with stochastic optimal control.
result ACSSM outperforms in tasks like classification, regression, interpolation, and extrapolation.
New method approximates POMDPs with PB-MDPs, providing error bounds and practical algorithms.
problem Difficulty in solving POMDPs with continuous or hybrid state and observation spaces.
method Bounding particle filtering error and adapting MDP algorithms to POMDPs.
result General theory and practical algorithms for POMDPs with no direct dependence on state and observation space sizes.
Extends GP models for sequential data, scalable and robust.
problem Handling sequential input-output observations in multi-task settings.
method Variational inference with sparse approximations and recursive GP priors.
result Tractable continual learning with KL divergences and recursive reconstruction.
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…
Predictive State Representations (PSRs) are an expressive class of models for controlled stochastic processes. PSRs represent state as a set of predictions of future observable events. Because PSRs are defined entirely in terms of observable data, statistically consistent estimates of PSR parameters can be learned effi…
A new method for binary ICA using non-stationary sources.
problem Independent component analysis of binary data.
method Linear mixing model in latent space, followed by binary observation model with non-stationary sources.
result Proves non-identifiability with few observed variables but identifies with more variables.
Efficiently infers coupled hidden Markov models with noisy discrete observations.
problem Intractable inference for coupled continuous-time Markov chains with discrete observations.
method Latent Interacting Particle Systems, look-ahead functions, twisted Sequential Monte Carlo sampling.
result Demonstrated effectiveness on latent SIRS model and wildfire spread dynamics.
Temporal-difference (TD) networks are a class of predictive state representations that use well-established TD methods to learn models of partially observable dynamical systems. Previous research with TD networks has dealt only with dynamical systems with finite sets of observations and actions. We present an algorithm…
We consider off-policy evaluation and optimization with continuous action spaces. We focus on observational data where the data collection policy is unknown and needs to be estimated. We take a semi-parametric approach where the value function takes a known parametric form in the treatment, but we are agnostic on how i…
Many reinforcement learning (RL) tasks provide the agent with high-dimensional observations that can be simplified into low-dimensional continuous states. To formalize this process, we introduce the concept of a DeepMDP, a parameterized latent space model that is trained via the minimization of two tractable losses: pr…
Multivariate categorical data occur in many applications of machine learning. One of the main difficulties with these vectors of categorical variables is sparsity. The number of possible observations grows exponentially with vector length, but dataset diversity might be poor in comparison. Recent models have gained sig…
Develops scalable methods to assess sensitivity and uncertainty in continuous treatment effects.
problem Estimating effects of continuous-valued interventions from observational data, especially when ignorability and positivity assumptions are violated.
method Continuous treatment-effect marginal sensitivity model (CMSM), scalable algorithm, uncertainty-aware deep models.
result Derives bounds that agree with observed data and a defined level of hidden confounding.
This research develops approximation theory for OOMs of infinite-dimensional processes.
problem Developing an approximation theory for OOMs of infinite-dimensional processes.
method Establishing an inner product structure and proving continuity of observable operators.
result A fundamental obstacle in making an infinite-dimensional space of future distributions into a Hilbert space is described.
Method infers MJPs from noisy observations without prior training.
problem Inference of MJPs from noisy and sparse observations is challenging.
method Broad probability distribution, synthetic dataset, and neural network model.
result Zero-shot inference of MJPs across different state spaces.
Neural Laplace Control tackles offline RL for continuous-time delayed systems with irregular observations.
problem Offline reinforcement learning problems involving continuous-time environments with delays and irregular observations.
method Combines a Neural Laplace dynamics model with a model predictive control (MPC) planner.
result Achieves near expert policy performance on continuous-time delayed environments.
The paper explores metrics on tree moduli spaces and a new topological group.
problem Continuous metrics on tree moduli spaces.
method Proposes and analyzes continuous piecewise-smooth metrics.
result Observes a new abelian topological group structure.
Modeling continuous movement of entities in latent space for interaction timing.
problem Analyzing timing and frequency of instantaneous interactions.
method Latent position model with continuous trajectories.
result Individual trajectories estimated from interaction data.
Paper introduces a new framework to improve sample efficiency in POMDPs learning.
problem Challenges in off-policy evaluation for POMDPs, especially with hidden states.
method Exploits the metric structure of belief space to relax coverage assumptions.
result Unified analysis technique yields tighter error bounds and sample efficiency improvements.
Continuous control tasks in reinforcement learning are important because they provide an important framework for learning in high-dimensional state spaces with deceptive rewards, where the agent can easily become trapped into suboptimal solutions. One way to avoid local optima is to use a population of agents to ensure…
HiPPO-Prophecy models can learn dynamical systems without fine-tuning.
problem Learning dynamical systems in context without fine-tuning parameters.
method Introduced a novel weight construction for SSMs that approximates derivatives of input signals.
result Discrete SSMs can predict the next state of any dynamical system after observing previous states.
A method for representing and comparing categorical trajectories using multivariate functional principal components.
problem Statistical description and comparison of categorical trajectories.
method Transforming categorical trajectories into binary indicator functions and applying multivariate functional principal components analysis.
result Consistent estimators of mean trajectories and covariance functions are obtained under weak regularity assumptions.
We prove strong consistency and asymptotic normality of least squares estimators for the subcritical Heston model based on continuous time observations. We also present some numerical illustrations of our results.
Efficient RL in large POMDPs with latent determinism and embeddings.
problem Efficient reinforcement learning in large-scale POMDPs with latent states and observations.
method Conditional Hilbert space embeddings, linear optimal Q-function, deterministic latent transitions, gap assumption. result Computationally and statistically efficient algorithm for exact optimal policy.
After learning a concept, humans are also able to continually generalize their learned concepts to new domains by observing only a few labeled instances without any interference with the past learned knowledge. In contrast, learning concepts efficiently in a continual learning setting remains an open challenge for curr…
Deep Reinforcement Learning (DRL) has been applied to address a variety of cooperative multi-agent problems with either discrete action spaces or continuous action spaces. However, to the best of our knowledge, no previous work has ever succeeded in applying DRL to multi-agent problems with discrete-continuous hybrid (…
The paper tackles noisy combinations of continuous and step functions, providing conditions for their identification.
problem Recovering noisy observations as a combination of continuous and step functions.
method Topological and local properties of the functions are used to determine conditions for identification. A practical estimation algorithm is provided.
result Conditions for the identification of continuous and step functions based on their global and local properties.
We study the dynamics of the Teichmuller flow in the moduli space of Abelian differentials (and more generally, its restriction to any connected component of a stratum). We show that the (Masur-Veech) absolutely continuous invariant probability measure is exponentially mixing for the class of Holder observables. A geom…
Proves FR-NGD optimally approximates evolutionary dynamics and continuous Bayesian inference.
problem Optimizing continuous time replicator equations and continuous Bayesian inference.
method Fisher-Rao natural gradient descent (FR-NGD) and its correspondence with evolutionary dynamics.
result FR-NGD optimally approximates continuous time replicator equations and continuous Bayesian inference.
Identifies latent actions and dynamics from offline data with diverse demonstrators.
problem Recovering latent actions and environment dynamics from action-free trajectories.
method Assumes distinct policies for each demonstrator, identifies latent transitions and policies via matrix factorization.
result Identifies latent transitions and demonstrator policies up to permutation.
A new model predicts network events with improved accuracy and interpretability.
problem Predicting and understanding complex dynamic relational data in networks.
method Mutually Exciting Latent Space Hawkes (LSH) model for continuous-time networks.
result The LSH model outperforms existing models in prediction accuracy and interpretability.
This paper finds a unique partition of a sample space for estimating continuous distributions.
problem Estimating continuous probability distributions from finite samples.
method Equal-probability partition of the sample space using order statistics.
result The partition yields an entropy of log2(N+1) bits, providing a discrete entropy estimate.