arXiv research

New model extracts shared brain activity patterns from fMRI data.

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…

Many dynamical systems exhibit similar structure, as often captured by hand-designed simplified models that can be used for analysis and control. We develop a method for learning to correspond pairs of dynamical systems via a learned latent dynamical system. Given trajectory data from two dynamical systems, we learn a …

FLUID uses flows to unify filtering and smoothing for complex systems.

Identifies latent actions and dynamics from offline data with diverse demonstrators.

StrEBM learns distinct latent components for better source separation.

For many complex diseases, there is a wide variety of ways in which an individual can manifest the disease. The challenge of personalized medicine is to develop tools that can accurately predict the trajectory of an individual's disease, which can in turn enable clinicians to optimize treatments. We represent an indivi…

We solve continuous-time latent SDE identifiability using diffusion shifts.

Generative model for SSc disease trajectories using deep learning.

In this work, we take a representation learning perspective on hierarchical reinforcement learning, where the problem of learning lower layers in a hierarchy is transformed into the problem of learning trajectory-level generative models. We show that we can learn continuous latent representations of trajectories, which…

The paper proposes a deep generative model for complex disease trajectories.

Modeling continuous movement of entities in latent space for interaction timing.

New algorithm infers trajectories from partial observations using optimal transport.

HCL learns shared and modality-specific latent representations for multimodal data.

TraLFM models human mobility patterns from traffic trajectories.

We link disjoint longitudinal data for rare disease patients using latent representations and mixed-effects regression.

A new framework models multi-state events and biomarkers.

LSS learns molecular trajectories from MD data.

A new method infers neural trajectories in real-time, improving experimental design.

New model for multiplex networks learns shared structure.

cvHM framework speeds up GP inference for neural spike train analysis.

Improved neural population modeling using shared features and ensemble detection.

New method disentangles shared and private latent factors in multimodal data.

EviTrack improves sequential prediction in delayed disambiguation scenarios.

LASER compresses recursive model activations by exploiting their low-dimensional structure.

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 metric compares noisy neural trajectories using optimal transport.

SPLICE method disentangles shared and private latent variables from multi-view data.

Map matching of GPS trajectories from a sequence of noisy observations serves the purpose of recovering the original routes in a road network. In this work in progress, we attempt to share our experience of feature construction in a spatial database by reporting our ongoing experiment of feature extrac-tion in Conditio…

We present a multi-task learning formulation for Deep Gaussian processes (DGPs), through non-linear mixtures of latent processes. The latent space is composed of private processes that capture within-task information and shared processes that capture across-task dependencies. We propose two different methods for segmen…

Fast algorithm for analyzing huge social networks.

New model captures state-dependent variability in partially observed systems.

Multi-task learning (MTL) allows deep neural networks to learn from related tasks by sharing parameters with other networks. In practice, however, MTL involves searching an enormous space of possible parameter sharing architectures to find (a) the layers or subspaces that benefit from sharing, (b) the appropriate amoun…

Develops MENT for interpreting and detecting changes in network trajectories.

MPE models traffic trajectory data to predict next locations.

Introduces alternators for modeling sequences, outperforming baselines.

We learn multiple hypotheses for related tasks under a latent hierarchical relationship between tasks. We exploit the intuition that for domain adaptation, we wish to share classifier structure, but for multitask learning, we wish to share covariance structure. Our hierarchical model is seen to subsume several previous…

Temporal prediction is critical for making intelligent and robust decisions in complex dynamic environments. Motion prediction needs to model the inherently uncertain future which often contains multiple potential outcomes, due to multi-agent interactions and the latent goals of others. Towards these goals, we introduc…

New method recovers diverse policies from expert data using state-action pair weighting.

UCB-TQL learns from multiple tasks with shared dynamics and adapts to task-specific variations.

This work explains how maximizing latent correlations across multiple data views helps in identifying shared and private components.

Method learns model for unknown stochastic system from data.

Predicts destinations and routes from partial trajectory data.

VLBM learns MDP transitions from limited data, improving OPE performance.

Multi-domain translation seeks to learn a probabilistic coupling between marginal distributions that reflects the correspondence between different domains. We assume that data from different domains are generated from a shared latent representation based on a structural equation model. Under this assumption, we show th…

In this paper we present a fully Bayesian latent variable model which exploits conditional nonlinear(in)-dependence structures to learn an efficient latent representation. The latent space is factorized to represent shared and private information from multiple views of the data. In contrast to previous approaches, we i…

CARE improves LLM aggregation by accounting for shared confounders.

Trajectory-level supervision allows efficient offline reinforcement learning.