From the 1 of 12 linked papers with an AI index.
12 papers
CaLiSym: Learning Symplectic Dynamics of Real-World Systems through Structured Canonical Lifts
Aristotelis Papatheodorou, Pranav Vaidhyanathan, Natalia Ares +2
The paper introduces CaLiSym, a framework that learns symplectic dynamics for real-world robotic systems by embedding states and ports into a lifted phase space, enabling accurate…
Action-Factored Multi-Agent Reinforcement Learning for Scalable Quantum Device Tuning
Edwin De Nicolo, Rahul Marchand, Cornelius Carlsson +2
Cooperative multi-agent reinforcement learning is well suited to problems with large parameter spaces and exploitable local structure, such as the tuning of electrostatically-defin…
A Physics-Inspired Optimizer: Velocity Regularized Adam
Pranav Vaidhyanathan, Lucas Schorling, Natalia Ares +1
We introduce Velocity-Regularized Adam (VRAdam), a physics-inspired optimizer for training deep neural networks that draws on ideas from quartic terms for kinetic energy with its s…
RIZZ: Routing Interactions to Near Zero-Interference Zones for Continual Adaptation of Black-Box Agents
Sonali Goel, Pranav Vaidhyanathan, Lucas Schorling +2
Large language models are increasingly deployed as long-lived agents that must adapt across users, tasks, domains, modalities, and feedback regimes without access to model weights.…
Canonical Regularisation of Wide Feature-Learning Neural Networks
George Whittle, Pranav Vaidhyanathan, Juliusz Ziomek +2
Wide neural networks in the feature-learning regime drive modern deep learning, and yet they remain far less studied than their kernel-regime counterparts. We consider a critical y…
Learning Physical Systems: Symplectification via Gauge Fixing in Dirac Structures
Aristotelis Papatheodorou, Pranav Vaidhyanathan, Natalia Ares +1
Physics-informed deep learning has achieved remarkable progress by embedding geometric priors, such as Hamiltonian symmetries and variational principles, into neural networks, enab…