Search Results for author:
Found 63 papers, 17 papers with code
Augmenting Continuous Time Bayesian Networks with Clocks
Structured stochastic processes evolving in continuous time present a widely adopted framework to model phenomena occurring in nature and engineering.
Bounded Rationality Equilibrium Learning in Mean Field Games
The resulting novel receding horizon (RH) MFGs are combined with QRE and existing approaches to model different aspects of bounded rationality in MFGs.
$\textit{GeoHard}$: Towards Measuring Class-wise Hardness through Modelling Class Semantics
Recent advances in measuring hardness-wise properties of data guide language models in sample selection within low-resource scenarios.
$\texttt{MixGR}$: Enhancing Retriever Generalization for Scientific Domain through Complementary Granularity
Recent studies show the growing significance of document retrieval in the generation of LLMs, i. e., RAG, within the scientific domain by bridging their knowledge gap.
FPGA-Based Neural Thrust Controller for UAVs
The advent of unmanned aerial vehicles (UAVs) has improved a variety of fields by providing a versatile, cost-effective and accessible platform for implementing state-of-the-art algorithms.
Scaling up Dynamic Edge Partition Models via Stochastic Gradient MCMC
For large network data, we propose a stochastic gradient Markov chain Monte Carlo (SG-MCMC) algorithm for scalable inference in the proposed model.
Negative-Binomial Randomized Gamma Markov Processes for Heterogeneous Overdispersed Count Time Series
Modeling count-valued time series has been receiving increasing attention since count time series naturally arise in physical and social domains.
A Poisson-Gamma Dynamic Factor Model with Time-Varying Transition Dynamics
Probabilistic approaches for handling count-valued time sequences have attracted amounts of research attentions because their ability to infer explainable latent structures and to estimate uncertainties, and thus are especially suitable for dealing with \emph{noisy} and \emph{incomplete} count data.
Graph Structure Inference with BAM: Introducing the Bilinear Attention Mechanism
In statistics and machine learning, detecting dependencies in datasets is a central challenge.
Approximate Control for Continuous-Time POMDPs
This work proposes a decision-making framework for partially observable systems in continuous time with discrete state and action spaces.
Learning Mean Field Games on Sparse Graphs: A Hybrid Graphex Approach
This hybrid graphex learning approach leverages that the system mainly consists of a highly connected core and a sparse periphery.
Collaborative Optimization of the Age of Information under Partial Observability
In this work, we devise a decentralized AoI-minimizing transmission policy for a number of sensor agents sharing capacity-limited, non-FIFO duplex channels that introduce random delays in communication with a common receiver.
Sparse Mean Field Load Balancing in Large Localized Queueing Systems
Empirically, the proposed methodology performs well on several realistic and scalable wireless network topologies as compared to a number of well-known load balancing heuristics and existing scalable multi-agent reinforcement learning methods.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
Learning Discrete-Time Major-Minor Mean Field Games
We propose a novel discrete time version of major-minor MFGs (M3FGs), along with a learning algorithm based on fictitious play and partitioning the probability simplex.
Learning to Cooperate and Communicate Over Imperfect Channels
In addition to this message size selection, agents learn to encode and decode messages to improve their jointly trained policies.
A Survey of Confidence Estimation and Calibration in Large Language Models
Assessing their confidence and calibrating them across different tasks can help mitigate risks and enable LLMs to produce better generations.
Entropic Matching for Expectation Propagation of Markov Jump Processes
This paper addresses the problem of statistical inference for latent continuous-time stochastic processes, which is often intractable, particularly for discrete state space processes described by Markov jump processes.
The TYC Dataset for Understanding Instance-Level Semantics and Motions of Cells in Microstructures
In this paper, we introduce the trapped yeast cell (TYC) dataset, a novel dataset for understanding instance-level semantics and motions of cells in microstructures.
Learning Decentralized Partially Observable Mean Field Control for Artificial Collective Behavior
However, multi-agent RL (MARL) remains a challenge in terms of decentralization, partial observability and scalability to many agents.
An Instance Segmentation Dataset of Yeast Cells in Microstructures
The aim of the dataset and evaluation strategy is to facilitate the development of new cell segmentation approaches.
Bayesian Inference for Jump-Diffusion Approximations of Biochemical Reaction Networks
The presented blocked Gibbs particle smoothing algorithm utilizes a sequential Monte Carlo method to estimate the latent states and performs distinct Gibbs steps for the parameters of a biochemical reaction network, by exploiting a jump-diffusion approximation model.
Probabilistic inverse optimal control for non-linear partially observable systems disentangles perceptual uncertainty and behavioral costs
Inverse optimal control can be used to characterize behavior in sequential decision-making tasks.
Major-Minor Mean Field Multi-Agent Reinforcement Learning
The algorithm is shown to approximate the policy gradient of the underlying M3FC MDP.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
Histopathological Image Classification based on Self-Supervised Vision Transformer and Weak Labels
Here, we propose Self-ViT-MIL, a novel approach for classifying and localizing cancerous areas based on slide-level annotations, eliminating the need for pixel-wise annotated training data.
Histopathological Image Classification
Image Classification
+1
Forward-Backward Latent State Inference for Hidden Continuous-Time semi-Markov Chains
We show that non-sampling-based latent state inference used in HSMM's can be generalized to latent Continuous-Time semi-Markov Chains (CTSMC's).
Reinforcement Learning with Non-Exponential Discounting
In contrast, in economics and psychology, it has been shown that humans often adopt a hyperbolic discounting scheme, which is optimal when a specific task termination time distribution is assumed.
Scalable Task-Driven Robotic Swarm Control via Collision Avoidance and Learning Mean-Field Control
Thus, we combine collision avoidance and learning of mean-field control into a unified framework for tractably designing intelligent robotic swarm behavior.
Mean Field Games on Weighted and Directed Graphs via Colored Digraphons
Graphon mean field games (GMFGs) on the other hand provide a scalable and mathematically well-founded approach to learning problems that involve a large number of connected agents.
Learning Sparse Graphon Mean Field Games
Although the field of multi-agent reinforcement learning (MARL) has made considerable progress in the last years, solving systems with a large number of agents remains a hard challenge.
A Survey on Large-Population Systems and Scalable Multi-Agent Reinforcement Learning
The analysis and control of large-population systems is of great interest to diverse areas of research and engineering, ranging from epidemiology over robotic swarms to economics and finance.
Decentralized Coordination in Partially Observable Queueing Networks
We consider communication in a fully cooperative multi-agent system, where the agents have partial observation of the environment and must act jointly to maximize the overall reward.
Learning Mean-Field Control for Delayed Information Load Balancing in Large Queuing Systems
In this work, we consider a multi-agent load balancing system, with delayed information, consisting of many clients (load balancers) and many parallel queues.
Markov Chain Monte Carlo for Continuous-Time Switching Dynamical Systems
Switching dynamical systems are an expressive model class for the analysis of time-series data.
Hypergraphon Mean Field Games
We propose an approach to modelling large-scale multi-agent dynamical systems allowing interactions among more than just pairs of agents using the theory of mean field games and the notion of hypergraphons, which are obtained as limits of large hypergraphs.
Yeast cell segmentation in microstructured environments with deep learning
We give an overview of the datasets recorded for training, validating and testing the networks, as well as a typical use-case.
Learning Graphon Mean Field Games and Approximate Nash Equilibria
Recent advances at the intersection of dense large graph limits and mean field games have begun to enable the scalable analysis of a broad class of dynamical sequential games with large numbers of agents.
OSS-Net: Memory Efficient High Resolution Semantic Segmentation of 3D Medical Data
Occupancy networks (O-Nets) are an alternative for which the data is represented continuously in a function space and 3D shapes are learned as a continuous decision boundary.
Variational Inference for Continuous-Time Switching Dynamical Systems
Since many areas, such as biology or discrete-event systems, are naturally described in continuous time, we present a model based on an Markov jump process modulating a subordinated diffusion process.
Load Balancing in Compute Clusters with Delayed Feedback
In this paper, we provide a partially observable (PO) model that captures the load balancing decisions in parallel buffered systems under limited information of delayed acknowledgements.
Multi-StyleGAN: Towards Image-Based Simulation of Time-Lapse Live-Cell Microscopy
Time-lapse fluorescent microscopy (TLFM) combined with predictive mathematical modelling is a powerful tool to study the inherently dynamic processes of life on the single-cell level.
Ranked #1 on
TFLM sequence generation
on TLFM dataset
Active Learning of Continuous-time Bayesian Networks through Interventions
We propose a novel criterion for experimental design based on a variational approximation of the expected information gain.
Nearest-Neighbor-based Collision Avoidance for Quadrotors via Reinforcement Learning
Collision avoidance algorithms are of central interest to many drone applications.
Discrete-Time Mean Field Control with Environment States
Multi-agent reinforcement learning methods have shown remarkable potential in solving complex multi-agent problems but mostly lack theoretical guarantees.
Deep Reinforcement Learning
Multi-agent Reinforcement Learning
+3
Moment-Based Variational Inference for Stochastic Differential Equations
We construct the variational process as a controlled version of the prior process and approximate the posterior by a set of moment functions.
Approximately Solving Mean Field Games via Entropy-Regularized Deep Reinforcement Learning
We show that all discrete-time finite MFGs with non-constant fixed point operators fail to be contractive as typically assumed in existing MFG literature, barring convergence via fixed point iteration.
Maximizing Information Gain for the Characterization of Biomolecular Circuits
Quantitatively predictive models of biomolecular circuits are important tools for the design of synthetic biology and molecular communication circuits.
Poisson channel with binary Markov input and average sojourn time constraint
Determining its capacity is an optimization problem with respect to two parameters: the average sojourn times of the promoter's active (ON) and inactive (OFF) state.
Attention-Based Transformers for Instance Segmentation of Cells in Microstructures
For the specific use case, the proposed method surpasses the state-of-the-art tools for semantic segmentation and additionally predicts the individual object instances.
Multiclass Yeast Segmentation in Microstructured Environments with Deep Learning
Cell segmentation is a major bottleneck in extracting quantitative single-cell information from microscopy data.
POMDPs in Continuous Time and Discrete Spaces
We consider the problem of optimal decision making in such discrete state and action space systems under partial observability.
Continuous-Time Bayesian Networks with Clocks
Structured stochastic processes evolving in continuous time present a widely adopted framework to model phenomena occurring in nature and engineering.
A Variational Perturbative Approach to Planning in Graph-based Markov Decision Processes
We present a novel approximate solution method for multi-agent Markov decision problems on graphs, based on variational perturbation theory.
Correlation Priors for Reinforcement Learning
Many decision-making problems naturally exhibit pronounced structures inherited from the characteristics of the underlying environment.
Scalable Structure Learning of Continuous-Time Bayesian Networks from Incomplete Data
Instead of sampling and scoring all possible structures individually, we assume the generator of the CTBN to be composed as a mixture of generators stemming from different structures.
Moment-Based Variational Inference for Markov Jump Processes
We propose moment-based variational inference as a flexible framework for approximate smoothing of latent Markov jump processes.
Cluster Variational Approximations for Structure Learning of Continuous-Time Bayesian Networks from Incomplete Data
Existing approximation techniques, such as sampling and low-order variational methods, either scale unfavorably in system size, or are unsatisfactory in terms of accuracy.
Collapsed Variational Inference for Nonparametric Bayesian Group Factor Analysis
Group factor analysis (GFA) methods have been widely used to infer the common structure and the group-specific signals from multiple related datasets in various fields including systems biology and neuroimaging.
Dependent Relational Gamma Process Models for Longitudinal Networks
Within the latent space, our framework models the birth and death dynamics of individual groups via a thinning function.
A Poisson Gamma Probabilistic Model for Latent Node-group Memberships in Dynamic Networks
We present a probabilistic model for learning from dynamic relational data, wherein the observed interactions among networked nodes are modeled via the Bernoulli Poisson link function, and the underlying network structure are characterized by nonnegative latent node-group memberships, which are assumed to be gamma distributed.
Social and Information Networks
Inverse Reinforcement Learning via Nonparametric Spatio-Temporal Subgoal Modeling
Advances in the field of inverse reinforcement learning (IRL) have led to sophisticated inference frameworks that relax the original modeling assumption of observing an agent behavior that reflects only a single intention.
A Bayesian Approach to Policy Recognition and State Representation Learning
Learning from demonstration (LfD) is the process of building behavioral models of a task from demonstrations provided by an expert.
Inverse Reinforcement Learning in Swarm Systems
Inverse reinforcement learning (IRL) has become a useful tool for learning behavioral models from demonstration data.
A variational approach to path estimation and parameter inference of hidden diffusion processes
We consider a hidden Markov model, where the signal process, given by a diffusion, is only indirectly observed through some noisy measurements.
