10 papers
ConicFlow: constrained Inference-time optimal control for flow matching models
Shervin Khalafi, Kasra Fallah, Sung Cho +3
We propose ConicFlow, which frames constrained sampling from a flow matching model at inference time as an optimal control problem that balances deviation from the pretrained traje…
Byzantine-Robust Federated Representation Learning
Leonardo F. Toso, James Anderson, Rafael Pinot +1
We study federated learning (FL) with adversarial clients, where the goal is to minimize the average loss of the honest (non-adversarial) clients without knowing their identity. Un…
On the Gradient Heterogeneity Dynamics of Adversarially Robust Federated Regression
Leonardo F. Toso, James Anderson, Nirupam Gupta +1
Federated learning (FL) is intrinsically heterogeneous: honest clients may have different data-generating models. On top of that, adversarial clients can make heterogeneity even mo…
On the Unification of Optimal Current Reference Theory for Wound Rotor Synchronous Machines
Maxfield Parson-Scherban, Kasra Fallah, Navid Rahbariasr +3
Controllers for motor drives typically require a current reference which will satisfy the requested torque subject to system constraints. This work generalizes existing current ref…
Multitask LQG Control: Performance and Generalization Bounds
Leonardo F. Toso, Kasra Fallah, Charis Stamouli +2
We study multitask learning for stochastic and partially observed control systems, focusing on the linear quadratic Gaussian (LQG) problem. Our goal is to learn a common stabilizin…
JEPA-Bisim: Learning Robust Visual Representations for Planning with Joint-Embedding Predictive World Models
Leonardo F. Toso, Davit Shadunts, Yunyang Lu +5
World models learned from high-dimensional visual observations allow agents to make decisions and plan directly in latent space, avoiding pixel-level reconstruction. However, recen…
Adversarially Robust Multitask Adaptive Control
Kasra Fallah, Leonardo F. Toso, James Anderson
We study adversarially robust multitask adaptive linear quadratic control; a setting where multiple systems collaboratively learn control policies under model uncertainty and adver…
Physics-informed learning under mixing: How physical knowledge speeds up learning
Anna Scampicchio, Leonardo F. Toso, Rahel Rickenbach +2
A major challenge in physics-informed machine learning is to understand how the incorporation of prior domain knowledge affects learning rates when data are dependent. Focusing on…
Policy Gradient Bounds in Multitask LQR
Charis Stamouli, Leonardo F. Toso, Anastasios Tsiamis +2
We analyze the performance of policy gradient in multitask linear quadratic regulation (LQR), where the system and cost parameters differ across tasks. The main goal of multitask L…
Learning Stabilizing Policies via an Unstable Subspace Representation
Leonardo F. Toso, Lintao Ye, James Anderson
We study the problem of learning to stabilize (LTS) a linear time-invariant (LTI) system. Policy gradient (PG) methods for control assume access to an initial stabilizing policy. H…