Alert button
Picture for Rudy Bunel

Rudy Bunel

Alert button

Dj

Expressive Losses for Verified Robustness via Convex Combinations

May 23, 2023
Alessandro De Palma, Rudy Bunel, Krishnamurthy Dvijotham, M. Pawan Kumar, Robert Stanforth, Alessio Lomuscio

Figure 1 for Expressive Losses for Verified Robustness via Convex Combinations
Figure 2 for Expressive Losses for Verified Robustness via Convex Combinations
Figure 3 for Expressive Losses for Verified Robustness via Convex Combinations
Figure 4 for Expressive Losses for Verified Robustness via Convex Combinations
Viaarxiv icon

Provably Correct Physics-Informed Neural Networks

May 17, 2023
Francisco Eiras, Adel Bibi, Rudy Bunel, Krishnamurthy Dj Dvijotham, Philip Torr, M. Pawan Kumar

Figure 1 for Provably Correct Physics-Informed Neural Networks
Figure 2 for Provably Correct Physics-Informed Neural Networks
Figure 3 for Provably Correct Physics-Informed Neural Networks
Figure 4 for Provably Correct Physics-Informed Neural Networks
Viaarxiv icon

DRIP: Domain Refinement Iteration with Polytopes for Backward Reachability Analysis of Neural Feedback Loops

Dec 09, 2022
Michael Everett, Rudy Bunel, Shayegan Omidshafiei

Figure 1 for DRIP: Domain Refinement Iteration with Polytopes for Backward Reachability Analysis of Neural Feedback Loops
Figure 2 for DRIP: Domain Refinement Iteration with Polytopes for Backward Reachability Analysis of Neural Feedback Loops
Figure 3 for DRIP: Domain Refinement Iteration with Polytopes for Backward Reachability Analysis of Neural Feedback Loops
Figure 4 for DRIP: Domain Refinement Iteration with Polytopes for Backward Reachability Analysis of Neural Feedback Loops
Viaarxiv icon

IBP Regularization for Verified Adversarial Robustness via Branch-and-Bound

Jun 29, 2022
Alessandro De Palma, Rudy Bunel, Krishnamurthy Dvijotham, M. Pawan Kumar, Robert Stanforth

Figure 1 for IBP Regularization for Verified Adversarial Robustness via Branch-and-Bound
Figure 2 for IBP Regularization for Verified Adversarial Robustness via Branch-and-Bound
Figure 3 for IBP Regularization for Verified Adversarial Robustness via Branch-and-Bound
Figure 4 for IBP Regularization for Verified Adversarial Robustness via Branch-and-Bound
Viaarxiv icon

Improved Branch and Bound for Neural Network Verification via Lagrangian Decomposition

Apr 14, 2021
Alessandro De Palma, Rudy Bunel, Alban Desmaison, Krishnamurthy Dvijotham, Pushmeet Kohli, Philip H. S. Torr, M. Pawan Kumar

Figure 1 for Improved Branch and Bound for Neural Network Verification via Lagrangian Decomposition
Figure 2 for Improved Branch and Bound for Neural Network Verification via Lagrangian Decomposition
Figure 3 for Improved Branch and Bound for Neural Network Verification via Lagrangian Decomposition
Figure 4 for Improved Branch and Bound for Neural Network Verification via Lagrangian Decomposition
Viaarxiv icon

Verifying Probabilistic Specifications with Functional Lagrangians

Feb 18, 2021
Leonard Berrada, Sumanth Dathathri, Krishnamurthy, Dvijotham, Robert Stanforth, Rudy Bunel, Jonathan Uesato, Sven Gowal, M. Pawan Kumar

Figure 1 for Verifying Probabilistic Specifications with Functional Lagrangians
Figure 2 for Verifying Probabilistic Specifications with Functional Lagrangians
Figure 3 for Verifying Probabilistic Specifications with Functional Lagrangians
Figure 4 for Verifying Probabilistic Specifications with Functional Lagrangians
Viaarxiv icon

Scaling the Convex Barrier with Sparse Dual Algorithms

Jan 26, 2021
Alessandro De Palma, Harkirat Singh Behl, Rudy Bunel, Philip H. S. Torr, M. Pawan Kumar

Figure 1 for Scaling the Convex Barrier with Sparse Dual Algorithms
Figure 2 for Scaling the Convex Barrier with Sparse Dual Algorithms
Figure 3 for Scaling the Convex Barrier with Sparse Dual Algorithms
Figure 4 for Scaling the Convex Barrier with Sparse Dual Algorithms
Viaarxiv icon

Scaling the Convex Barrier with Active Sets

Jan 14, 2021
Alessandro De Palma, Harkirat Singh Behl, Rudy Bunel, Philip H. S. Torr, M. Pawan Kumar

Figure 1 for Scaling the Convex Barrier with Active Sets
Figure 2 for Scaling the Convex Barrier with Active Sets
Figure 3 for Scaling the Convex Barrier with Active Sets
Figure 4 for Scaling the Convex Barrier with Active Sets
Viaarxiv icon

Enabling certification of verification-agnostic networks via memory-efficient semidefinite programming

Nov 03, 2020
Sumanth Dathathri, Krishnamurthy Dvijotham, Alexey Kurakin, Aditi Raghunathan, Jonathan Uesato, Rudy Bunel, Shreya Shankar, Jacob Steinhardt, Ian Goodfellow, Percy Liang, Pushmeet Kohli

Figure 1 for Enabling certification of verification-agnostic networks via memory-efficient semidefinite programming
Figure 2 for Enabling certification of verification-agnostic networks via memory-efficient semidefinite programming
Figure 3 for Enabling certification of verification-agnostic networks via memory-efficient semidefinite programming
Figure 4 for Enabling certification of verification-agnostic networks via memory-efficient semidefinite programming
Viaarxiv icon

An efficient nonconvex reformulation of stagewise convex optimization problems

Oct 27, 2020
Rudy Bunel, Oliver Hinder, Srinadh Bhojanapalli, Krishnamurthy, Dvijotham

Figure 1 for An efficient nonconvex reformulation of stagewise convex optimization problems
Figure 2 for An efficient nonconvex reformulation of stagewise convex optimization problems
Figure 3 for An efficient nonconvex reformulation of stagewise convex optimization problems
Figure 4 for An efficient nonconvex reformulation of stagewise convex optimization problems
Viaarxiv icon