Search Results for author:
Found 8 papers, 2 papers with code
Tight Certified Robustness via Min-Max Representations of ReLU Neural Networks
The reliable deployment of neural networks in control systems requires rigorous robustness guarantees.
Projected Randomized Smoothing for Certified Adversarial Robustness
Randomized smoothing is the current state-of-the-art method for producing provably robust classifiers.
Initial State Interventions for Deconfounded Imitation Learning
Imitation learning suffers from causal confusion.
Meta-Learning Parameterized First-Order Optimizers using Differentiable Convex Optimization
Conventional optimization methods in machine learning and controls rely heavily on first-order update rules.
LQR Control with Sparse Adversarial Disturbances
Under mild conditions, we show that the disturbance-aware policy converges to the blind online policy if the number of disturbances grows sublinearly in the time horizon.
Safe Reinforcement Learning with Chance-constrained Model Predictive Control
Real-world reinforcement learning (RL) problems often demand that agents behave safely by obeying a set of designed constraints.
Discriminability of Single-Layer Graph Neural Networks
We define a notion of discriminability tied to the stability of the architecture, show that GNNs are at least as discriminative as linear graph filter banks, and characterize the signals that cannot be discriminated by either.
ContactNets: Learning Discontinuous Contact Dynamics with Smooth, Implicit Representations
Common methods for learning robot dynamics assume motion is continuous, causing unrealistic model predictions for systems undergoing discontinuous impact and stiction behavior.
