Search Results for author:
Found 12 papers, 3 papers with code
Length Optimization in Conformal Prediction
Conditional validity and length efficiency are two crucial aspects of conformal prediction (CP).
Explicitly Encoding Structural Symmetry is Key to Length Generalization in Arithmetic Tasks
Empirically, our method allows a Transformer trained on numbers with at most 5-digits for addition and multiplication to generalize up to 50-digit numbers, without using additional data for longer sequences.
Conformal Prediction with Learned Features
In this paper, we focus on the problem of conformal prediction with conditional guarantees.
Risk Verification of Stochastic Systems with Neural Network Controllers
Motivated by the fragility of neural network (NN) controllers in safety-critical applications, we present a data-driven framework for verifying the risk of stochastic dynamical systems with NN controllers.
Toward Certified Robustness Against Real-World Distribution Shifts
We consider the problem of certifying the robustness of deep neural networks against real-world distribution shifts.
Exploiting Heterogeneity in Robust Federated Best-Arm Identification
We study a federated variant of the best-arm identification problem in stochastic multi-armed bandits: a set of clients, each of whom can sample only a subset of the arms, collaborate via a server to identify the best arm (i. e., the arm with the highest mean reward) with prescribed confidence.
Autoencoder-driven Spiral Representation Learning for Gravitational Wave Surrogate Modelling
Based on this finding, we design a spiral module with learnable parameters, that is used as the first layer in a neural network, which learns to map the input space to the coefficients.
Can supermassive black hole shadows test the Kerr metric?
The unprecedented image of the M87* supermassive black hole has sparked some controversy over its usefulness as a test of the general relativistic Kerr metric.
General Relativity and Quantum Cosmology High Energy Astrophysical Phenomena
A Temporal Logic-Based Hierarchical Network Connectivity Controller
We show that these constraints along with the requirement of propagating information in the network can be captured by a Linear Temporal Logic (LTL) framework.
The surface of rapidly-rotating neutron stars: implications to neutron star parameter estimation
We also find evidence that the formula currently used by NICER can be used in the inference of the radii of rapidly rotating stars, outside of the formula's domain of validity.
High Energy Astrophysical Phenomena General Relativity and Quantum Cosmology
Online Learning of the Kalman Filter with Logarithmic Regret
When the system model is unknown, we have to learn how to predict observations online based on finite data, suffering possibly a non-zero regret with respect to the Kalman filter's prediction.
Learning Decentralized Controllers for Robot Swarms with Graph Neural Networks
We consider the problem of finding distributed controllers for large networks of mobile robots with interacting dynamics and sparsely available communications.
Robotics
