Alec Farid
YOU?
Author Swipe
View article: Task-Relevant Failure Detection for Trajectory Predictors in Autonomous Vehicles
Task-Relevant Failure Detection for Trajectory Predictors in Autonomous Vehicles Open
In modern autonomy stacks, prediction modules are paramount to planning motions in the presence of other mobile agents. However, failures in prediction modules can mislead the downstream planner into making unsafe decisions. Indeed, the hi…
View article: Failure Prediction with Statistical Guarantees for Vision-Based Robot Control
Failure Prediction with Statistical Guarantees for Vision-Based Robot Control Open
We are motivated by the problem of performing failure prediction for safety-critical robotic systems with highdimensional sensor observations (e.g., vision).Given access to a black-box control policy (e.g., in the form of a neural network)…
View article: Towards a Framework for Comparing the Complexity of Robotic Tasks
Towards a Framework for Comparing the Complexity of Robotic Tasks Open
We are motivated by the problem of comparing the complexity of one robotic task relative to another. To this end, we define a notion of reduction that formalizes the following intuition: Task 1 reduces to Task 2 if we can efficiently trans…
View article: Failure Prediction with Statistical Guarantees for Vision-Based Robot Control
Failure Prediction with Statistical Guarantees for Vision-Based Robot Control Open
We are motivated by the problem of performing failure prediction for safety-critical robotic systems with high-dimensional sensor observations (e.g., vision). Given access to a black-box control policy (e.g., in the form of a neural networ…
View article: Task-Driven Detection of Distribution Shifts with Statistical Guarantees for Robot Learning
Task-Driven Detection of Distribution Shifts with Statistical Guarantees for Robot Learning Open
Our goal is to perform out-of-distribution (OOD) detection, i.e., to detect when a robot is operating in environments drawn from a different distribution than the ones used to train the robot. We leverage Probably Approximately Correct (PA…
View article: Task-Driven Out-of-Distribution Detection with Statistical Guarantees for Robot Learning.
Task-Driven Out-of-Distribution Detection with Statistical Guarantees for Robot Learning. Open
Our goal is to perform out-of-distribution (OOD) detection, i.e., to detect when a robot is operating in environments that are drawn from a different distribution than the environments used to train the robot. We leverage Probably Approxim…
View article: Generalization Bounds for Meta-Learning via PAC-Bayes and Uniform Stability
Generalization Bounds for Meta-Learning via PAC-Bayes and Uniform Stability Open
We are motivated by the problem of providing strong generalization guarantees in the context of meta-learning. Existing generalization bounds are either challenging to evaluate or provide vacuous guarantees in even relatively simple settin…
View article: PAC-BUS: Meta-Learning Bounds via PAC-Bayes and Uniform Stability.
PAC-BUS: Meta-Learning Bounds via PAC-Bayes and Uniform Stability. Open
We are motivated by the problem of providing strong generalization guarantees in the context of meta-learning. Existing generalization bounds are either challenging to evaluate or provide vacuous guarantees in even relatively simple settin…
View article: Generalization Bounds for Meta-Learning via PAC-Bayes and Uniform\n Stability
Generalization Bounds for Meta-Learning via PAC-Bayes and Uniform\n Stability Open
We are motivated by the problem of providing strong generalization guarantees\nin the context of meta-learning. Existing generalization bounds are either\nchallenging to evaluate or provide vacuous guarantees in even relatively simple\nset…
View article: PAC-Bayes control: learning policies that provably generalize to novel environments
PAC-Bayes control: learning policies that provably generalize to novel environments Open
Our goal is to learn control policies for robots that provably generalize well to novel environments given a dataset of example environments. The key technical idea behind our approach is to leverage tools from generalization theory in mac…