New algorithm infers trajectories from partial observations using optimal transport.
problem Inferring trajectories from partial observations of coupled systems.
method Extends MFL algorithm to latent SDEs using observable state space models and partial observations.
result Experiments show significant outperformance over latent-free baseline.
DGFS improves sampling from complex densities by optimizing partial trajectories.
problem Sampling from intractable high-dimensional density functions.
method DGFS uses a flow function to break down the training process into short partial trajectory segments, leveraging intermediate learning signals.
result DGFS achieves more accurate estimates of the normalization constant.
Predicts destinations and routes from partial trajectory data.
problem Predicting destinations and routes from partial trajectory data for applications like parking suggestions and ride-sharing.
method Three-step procedure: k-d tree-based space discretization, recurrent neural network for destination prediction, and route calculation.
result Best models predict destinations with a mean error of 1.3 km and 1.43 km.
For a non-vanishing gradient-like vector field on a compact manifold Xn+1 with boundary, a discrete set of trajectories may be tangent to the boundary with reduced multiplicity n, which is the maximum possible. (Among them are trajectories that are tangent to ∂X exactly n times.) We prove a lower bou…
FDNet learns PDEs from data with fast predictions.
problem Discovering complex systems behavior from data.
method Finite difference neural networks (FDNet) to learn PDEs from trajectory data.
result FDNet predicts future behavior with few trainable parameters.
Enhances reinforcement learning from sparse data.
problem Limited data for offline reinforcement learning.
method Trajectory-based data augmentation.
result Improves reinforcement learning performance.
DISCO predicts system states from short trajectories using an evolved operator.
problem Predicting next states of dynamical systems governed by unknown PDEs.
method DISCO uses a hypernetwork to generate parameters of a smaller operator network for state prediction.
result DISCO achieves state-of-the-art performance with fewer training epochs and generalizes well.
New data improves market impact estimation methods.
problem Improving efficiency of market impact estimation.
method Investigates the use of price trajectory data for market impact estimation.
result Estimation methods using early trade prices outperform established methods asymptotically.
New model captures state-dependent variability in partially observed systems.
problem Structured stochasticity not captured by constant-variance models.
method State-coupled stochastic volatility framework with particle expectation-maximization.
result Model consistently reduces recovery bias under partial observation.
Generative model learns vehicle trajectory distributions for better data generalization.
problem Data sparsity and privacy issues in urban vehicle trajectory analysis.
method Generative adversarial imitation learning framework for urban vehicle trajectory generation.
result TrajGAIL model produces synthetic trajectories similar to real ones, achieving significant performance gains.
We propose a method to model multi-agent behaviors with limited observation and mechanical constraints.
problem Modeling real-world multi-agent behaviors with limited observation and mechanical constraints.
method Decentralized generative models with partial observation and mechanical constraints based on hierarchical variational recurrent neural networks.
result Our method effectively models and predicts biologically plausible behaviors with minimal constraint violations.
In this paper we propose a new method to predict the final destination of vehicle trips based on their initial partial trajectories. We first review how we obtained clustering of trajectories that describes user behaviour. Then, we explain how we model main traffic flow patterns by a mixture of 2d Gaussian distribution…
Developed a random walk analog of geodesic flow on hyperbolic groups.
problem Geodesic flow on hyperbolic groups due to non-uniqueness of geodesics.
method Introduced a new framework using random walks and bi-infinite trajectories.
result Established ergodicity of the randomized geodesic flow and exponential mixing.
Method learns dynamics from aggregate data without full trajectories.
problem Learning nonlinear dynamics from aggregate data where individual trajectories are not available.
method Combines weak Fokker-Planck Equation description with Wasserstein GAN.
result Successfully learns nonlinear dynamics from aggregate data.
Deep learning approximates SPDE solutions from noise trajectories.
problem Approximating solutions to stochastic partial differential equations (SPDEs).
method Uses neural networks to approximate SPDE solutions based on noise realizations.
result Accurately estimates SPDE solutions and functionals like mean and variance.
Paper proposes learning system dynamics from irregularly-sampled partial observations.
problem Capturing dynamics of multi-agent systems with irregular and partial observations.
method LG-ODE, a latent ordinary differential equation model using graph neural networks and neuralODE.
result Demonstrates effectiveness on motion capture, spring system, and charged particle datasets.
Suppose (X,J,ω) is a Fano manifold and t→rt is a diverging Kähler-Ricci trajectory. We construct a bounded geodesic ray t→ut weakly asymptotic to t→rt, along which Ding's F-functional decreases, partially confirming a folklore conjecture. In absence of non-trivial holomorphic vector fi…
Data driven methods for time series forecasting that quantify uncertainty open new important possibilities for robot tasks with hard real time constraints, allowing the robot system to make decisions that trade off between reaction time and accuracy in the predictions. Despite the recent advances in deep learning, it i…
Bayesian inference models failure distributions in autonomous systems.
problem Estimating the distribution of failures in complex systems.
method Bayesian inference using system dynamics rollouts and gradient computation.
result Improves sample efficiency and parameter space coverage in autonomous systems.
We study partial collapsing degeneration of Hamiltonian-perturbed Floer trajectories for an adiabatic ε-family and its reversal adiabatic gluing, as the prototype of the partial collapsing degeneration of 2-dimensional (perturbed) J-holomorphic maps to 1-dimensional gradient segments. We consider the …
We present a data-efficient reinforcement learning algorithm resistant to observation noise. Our method extends the highly data-efficient PILCO algorithm (Deisenroth & Rasmussen, 2011) into partially observed Markov decision processes (POMDPs) by considering the filtering process during policy evaluation. PILCO conduct…
Learning the parameters of a (potentially partially observable) random field model is intractable in general. Instead of focussing on a single optimal parameter value we propose to treat parameters as dynamical quantities. We introduce an algorithm to generate complex dynamics for parameters and (both visible and hidde…
This work characterizes reward function partial identifiability and its impact on policy optimization.
problem Reward function partial identifiability in complex tasks.
method Formal characterisation of partial identifiability using various reward learning data sources.
result Unified framework for comparing data sources and downstream tasks by their invariances.
We present a method that learns to integrate temporal information, from a learned dynamics model, with ambiguous visual information, from a learned vision model, in the context of interacting agents. Our method is based on a graph-structured variational recurrent neural network (Graph-VRNN), which is trained end-to-end…
Rigidity of travel times for convex obstacles in Riemannian manifolds is proven.
problem Rigidity of travel times for strictly convex obstacles in Riemannian manifolds.
method Analysis of billiard trajectories and comparison of travel times.
result If travel times are equal, then obstacles are identical in dimensions greater than or equal to 3.
Calibrated PRMs improve inference efficiency for LLMs by dynamically adjusting compute budgets.
problem Poor calibration of PRMs leads to overestimation of success probabilities in partial reasoning steps.
method Quantile regression for calibration, instance-adaptive scaling (IAS) framework.
result Calibrated PRMs reduce inference costs while maintaining accuracy, especially on confident problems.
A large body of animation research focuses on optimization of movement control, either as action sequences or policy parameters. However, as closed-form expressions of the objective functions are often not available, our understanding of the optimization problems is limited. Building on recent work on analyzing neural …
Persistent neurons improve neural network optimization by leveraging previous solutions.
problem Improving neural network optimization under different initialization and data distributions.
method Persistent neurons use information from previous converged solutions to explore new landscapes and avoid local minima.
result Persistent neurons converge to more optimal solutions and improve model performance under various initializations.
TNDE quantifies dynamic gene drivers from single-cell snapshots.
problem Reconstructing time-resolved regulatory effects in biological processes.
method Time-varying Network Driver Estimation (TNDE) using shared graph attention encoder and partial optimal transport.
result TNDE identifies stage-specific driver genes in mouse erythropoiesis.
We consider the problem of learning from demonstrated trajectories with inverse reinforcement learning (IRL). Motivated by a limitation of the classical maximum entropy model in capturing the structure of the network of states, we propose an IRL model based on a generalized version of the causal entropy maximization pr…
RLHF fails when humans only partially observe, leading to inflated or overjustified feedback.
problem Failure of reinforcement learning from human feedback in partially observable environments.
method Formal definition of failure cases, modeling human as Boltzmann rational, analyzing information provided by feedback.
result RLHF can deceptively inflate or overjustify feedback when humans have partial observations.
Neural surrogate predicts SPN rates from token trajectories.
problem Challenging parameter estimation in SPNs with covariates.
method 1D Convolutional Residual Network trained on Gillespie-simulated SPN realizations.
result Surrogate predicts rate-function coefficients with RMSE = 0.043.
The paper explores invariant subbundles in nonholonomic mechanics.
problem Determining invariant affine subbundles in nonholonomic and constrained variational mechanics.
method Using Spencer cohomology and iterative formulae, the paper formalizes the integrability of linear partial differential equations and determines the largest invariant affine subbundle.
result Iterative formulae for determining the largest invariant affine subbundle are provided.
Symmetry groups of PDEs allow to transform solutions continuously into other solutions. In this paper, we use this property for the observability analysis of nonlinear PDEs with input and output. Based on a differential-geometric representation of the nonlinear system, we derive conditions for the existence of special …
Let T⊂Rm+1 be a strictly convex domain bounded by a smooth hypersurface X=∂T. In this paper we find lower bounds on the number of billiard trajectories in T which have a prescribed intial point A∈X, a prescribed final point B∈X and make a prescribed number n of reflections at the bo…
This work frames active inference through control as inference, offering robust control algorithms.
problem Active inference framework lacks practical sensorimotor control algorithms.
method Frame active inference through control as inference, presenting trajectory optimization as inference.
result AI may be framed as partially-observed CaI when the cost function is defined in observation states.
Study supports recovery of PDEs from noisy data using a specific regularization method.
problem Support recovery of PDEs from a single noisy trajectory.
method Applying ℓ1-regularized Pseudo-Least Squares model to a given data set.
result Support of ℓ1-c coefficients asymptotically converges to the true signed-support of the PDE.
Improved neural PDEs trained on augmented data enhance model accuracy and efficiency.
problem Training neural PDEs on limited data to accurately represent complex systems.
method Space-filling sampling of local states to generate augmented training data.
result Data-augmented neural PDEs outperform traditional emulators in accuracy and stability.
Paper establishes a generalization bound for gradient flow using a data-dependent kernel.
problem Understanding the generalization properties of gradient-based optimization methods.
method Establishes a generalization bound for gradient flow through a data-dependent kernel called the loss path kernel (LPK).
result The LPK captures the entire training trajectory and leads to tighter generalization guarantees.
New method reduces PDE surrogate model training costs by selectively acquiring time steps.
problem High computational cost of generating training data for PDE surrogate models.
method STAP (Selective Time-Step Acquisition for PDEs) framework that acquires only important time steps.
result Demonstrated effectiveness on several benchmark PDEs, reducing training costs.
CoLoRA models predict PDE solutions quickly and accurately with minimal data.
problem Efficiently modeling PDE solutions with limited data.
method Continuous low-rank adaptation of neural networks trained on offline data.
result Predictions are orders of magnitude faster and more accurate than classical methods.
New algorithm tackles confounding in offline RL for partially observable MDPs.
problem Confounding in offline reinforcement learning for partially observable MDPs.
method P3O algorithm using proximal causal inference and pessimistic confidence regions.
result Achieves n−1/2-suboptimality for offline RL in POMDPs with confounded data. New method trains GFlowNets from partial episodes to improve convergence and stability.
problem Improving convergence and stability of GFlowNets training.
method Introducing SubTB(λ) for GFlowNet training from partial action subsequences. result SubTB(λ) accelerates GFlowNet convergence and enables training in longer action sequences. We study smooth {\sf traversing} vector fields v on compact manifolds X with boundary. A traversing v admits a Lyapunov function f:X→R such that df(v)>0. We show that the trajectory spaces T(v) of {\sf traversally generic} v-flows are {\sf Whitney stratified spaces}, and thus admit tr…
Imitation learning targets deriving a mapping from states to actions, a.k.a. policy, from expert demonstrations. Existing methods for imitation learning typically require any actions in the demonstrations to be fully available, which is hard to ensure in real applications. Though algorithms for learning with unobservab…
Investors pay for additional asset information based on utility maximization.
problem Determining the optimal price for additional asset information.
method Solving a stochastic control problem with partial information and utility maximization.
result Investors choose to purchase information at a deterministic time.
PRL improves off-policy evaluation in partially observed MDPs.
problem Confounding and bias in offline reinforcement learning with unobserved state factors.
method Extends proximal causal inference to POMDPs, identifying and estimating target policy value.
result Semiparametrically efficient estimators for PRL in partially observed MDPs.
The paper develops a method to learn navigation costs from expert demonstrations in partially observable environments.
problem Learning navigation costs from expert demonstrations in partially observable environments.
method Develops a cost function representation composed of a probabilistic occupancy encoder and a cost encoder, optimized by differentiating the error between demonstrated controls and a control policy computed from the cost encoder.
result The method outperforms baseline IRL algorithms in robot navigation tasks, improving both training and test-time efficiency.