A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
Paper proposes transferring neural network learning trajectories.
Improved trajectory prediction for team sports using sparse outputs.
Generative model learns vehicle trajectory distributions for better data generalization.
We address the problem of abnormal event detection from trajectory data. In this paper, a new adversarial approach is proposed for building a deep neural network binary classifier, trained in an unsupervised fashion, that can distinguish normal from abnormal trajectory-based events without the need for setting manual d…
The paper investigates how neural network weights evolve to monitor training progress.
In this paper, we propose a reinforcement learning-based algorithm for trajectory optimization for constrained dynamical systems. This problem is motivated by the fact that for most robotic systems, the dynamics may not always be known. Generating smooth, dynamically feasible trajectories could be difficult for such sy…
Reasoning models generate differently based on problem difficulty, not just length.
Captures data influence changes during training.
The study analyzes optimization trajectories in neural networks to reveal redundancy and redundancy-reducing strategies.
Cohen et al. (2021) show GD trajectories align on a bifurcation diagram.
Variational inference improves training of generative flow networks.
Study shows different trajectory prediction models generalize better under OoD conditions.
TGD improves conditional sampling by concentrating computation on promising trajectories.
We introduce a generative adversarial network (GAN) model to simulate the 3-dimensional Lagrangian motion of particles trapped in the recirculation zone of a buoyancy-opposed flame. The GAN model comprises a stochastic recurrent neural network, serving as a generator, and a convoluted neural network, serving as a discr…
One technique to visualize the training of neural networks is to perform PCA on the parameters over the course of training and to project to the subspace spanned by the first few PCA components. In this paper we compare this technique to the PCA of a high dimensional random walk. We compute the eigenvalues and eigenvec…
Method predicts NBA players' multi-modal movement trajectories.
Efficiently trains forward processes to minimize generative trajectories curvature.
In this paper, we focus on the development of a method that detects abnormal trajectories of road users at traffic intersections. The main difficulty with this is the fact that there are very few abnormal data and the normal ones are insufficient for the training of any kinds of machine learning model. To tackle these …
Trajectory optimization using a learned model of the environment is one of the core elements of model-based reinforcement learning. This procedure often suffers from exploiting inaccuracies of the learned model. We propose to regularize trajectory optimization by means of a denoising autoencoder that is trained on the …
Deep Reinforcement Learning has shown tremendous success in solving several games and tasks in robotics. However, unlike humans, it generally requires a lot of training instances. Trajectories imitating to solve the task at hand can help to increase sample-efficiency of deep RL methods. In this paper, we present a simp…
Representation learning of pedestrian trajectories transforms variable-length timestamp-coordinate tuples of a trajectory into a fixed-length vector representation that summarizes spatiotemporal characteristics. It is a crucial technique to connect feature-based data mining with trajectory data. Trajectory representati…
WS-II algorithm segments trajectories with high accuracy.
Enhances reinforcement learning from sparse data.
We consider the problem of recovering an expert's reward function with inverse reinforcement learning (IRL) when there are missing/incomplete state-action pairs or observations in the demonstrated trajectories. This issue of missing trajectory data or information occurs in many situations, e.g., GPS signals from vehicl…
CCM improves context for Meta-RL by contrastive learning.
New method models unknown systems with hidden parameters using neural networks.
When governed by underlying low-dimensional dynamics, the interdependence of simultaneously recorded population of neurons can be explained by a small number of shared factors, or a low-dimensional trajectory. Recovering these latent trajectories, particularly from single-trial population recordings, may help us unders…
Improved neural PDEs trained on augmented data enhance model accuracy and efficiency.
Analyzing the urban trajectory in cities has become an important topic in data mining. How can we model the human mobility consisting of stay and travel from the raw trajectory data? How can we infer such a mobility model from the single trajectory information? How can we further generalize the mobility inference to ac…
SciSports is a Dutch startup company specializing in football analytics. This paper describes a joint research effort with SciSports, during the Study Group Mathematics with Industry 2018 at Eindhoven, the Netherlands. The main challenge that we addressed was to automatically process empirical football players' traject…
This paper presents a novel framework for accurate pedestrian intent prediction at intersections. Given some prior knowledge of the curbside geometry, the presented framework can accurately predict pedestrian trajectories, even in new intersections that it has not been trained on. This is achieved by making use of the …
New method improves meta-reinforcement learning efficiency.
Navigating complex urban environments safely is a key to realize fully autonomous systems. Predicting future locations of vulnerable road users, such as pedestrians and cyclists, thus, has received a lot of attention in the recent years. While previous works have addressed modeling interactions with the static (obstacl…
Proposes a model for generating survival trajectories and data.
New method for data assimilation using score-based models.
GT-DDP optimizer trains residual networks using game theory.
Model-free reinforcement learning algorithms such as Deep Deterministic Policy Gradient (DDPG) often require additional exploration strategies, especially if the actor is of deterministic nature. This work evaluates the use of model-based trajectory optimization methods used for exploration in Deep Deterministic Policy…
New bounds on trajectory safety in training models with Langevin Dynamics.
New algorithm improves RL performance across different environments.
KOMET identifies Koopman operators from model parameter trajectories to adapt to evolving data distributions.
Adaptive stopping in MCMC using classifier-based dynamics
Stable GFlowNets prevent loss spikes and mode collapse in training.
Patients initially diagnosed with early mild cognitive impairment (eMCI) are known to be a clinically heterogeneous group with very subtle patterns of brain atrophy. To examine the boarders between normal controls (NC) and eMCI, Magnetic Resonance Imaging (MRI) was extensively used as a non-invasive imaging modality to…
We introduce a deep learning method to simulate the motion of particles trapped in a chaotic recirculating flame. The Lagrangian trajectories of particles, captured using a high-speed camera and subsequently reconstructed in 3-dimensional space, were used to train a variational autoencoder (VAE) which comprises multipl…
Improves neural relational inference for dynamic multi-agent trajectories.
TFM trains Neural SDEs without backpropagation, improving clinical time series modeling.
Generative model learns to mimic time-series behavior to generate accurate trajectories.
DGFS improves sampling from complex densities by optimizing partial trajectories.