activity
20242026
collaborators
Showing cs.LGShow all

15 papers · 1 filter

cs.LG2026

Q-Net: Queue Length Estimation via Kalman-based Neural Networks

Ting Gao, Elvin Isufi, Winnie Daamen +2

Estimating queue lengths at signalized intersections is a long-standing challenge in traffic management. Partial observability of vehicle flows complicates this task despite the av…

cs.LG2026

Flow Matching Policy Optimization with Mirror Descent and Entropy Constraints

Ting Gao, Stavros Orfanoudakis, Nan Lin +3

Balancing policy expressiveness with the exploration-exploitation trade-off is a core challenge in online Reinforcement Learning (RL). While Stochastic Differential Equation (SDE)-…

cs.LG2026

Stochastic Sequential Decision Making over Expanding Networks with Graph Filtering

Zhan Gao, Bishwadeep Das, Elvin Isufi

Graph filters leverage topological information to process networked data with existing methods mainly studying fixed graphs, ignoring that graphs often expand as nodes continually…

cs.LG2026

Directed Semi-Simplicial Learning with Applications to Brain Activity Decoding

Manuel Lecha, Andrea Cavallo, Francesca Dominici +5

Graph Neural Networks (GNNs) excel at learning from pairwise interactions but often overlook multi-way and hierarchical relationships. Topological Deep Learning (TDL) addresses thi…

cs.LG2026

Precision Neural Networks: Joint Graph And Relational Learning

Andrea Cavallo, Samuel Rey, Antonio G. Marques +1

CoVariance Neural Networks (VNNs) perform convolutions on the graph determined by the covariance matrix of the data, which enables expressive and stable covariance-based learning.…

cs.LG2025

Covariance Scattering Transforms

Andrea Cavallo, Ayushman Raghuvanshi, Sundeep Prabhakar Chepuri +1

Machine learning and data processing techniques relying on covariance information are widespread as they identify meaningful patterns in unsupervised and unlabeled settings. As a p…