no code implementations • 7 May 2024 • Rudy Bunel, Krishnamurthy, Dvijotham, M. Pawan Kumar, Alessandro De Palma, Robert Stanforth
Furthermore, we show that the complexity of the network (number of neurons/layers) can be adapted to the problem difficulty and solve problems where traditional compressed sensing methods are not known to provably work.
1 code implementation • 23 May 2023 • Alessandro De Palma, Rudy Bunel, Krishnamurthy Dvijotham, M. Pawan Kumar, Robert Stanforth, Alessio Lomuscio
In order to train networks for verified adversarial robustness, it is common to over-approximate the worst-case loss over perturbation regions, resulting in networks that attain verifiability at the expense of standard performance.
no code implementations • 17 May 2023 • Francisco Eiras, Adel Bibi, Rudy Bunel, Krishnamurthy Dj Dvijotham, Philip Torr, M. Pawan Kumar
Recent work provides promising evidence that Physics-informed neural networks (PINN) can efficiently solve partial differential equations (PDE).
1 code implementation • 9 Dec 2022 • Michael Everett, Rudy Bunel, Shayegan Omidshafiei
To address this issue, we introduce DRIP, an algorithm with a refinement loop on the relaxation domain, which substantially tightens the BP set bounds.
1 code implementation • 29 Jun 2022 • Alessandro De Palma, Rudy Bunel, Krishnamurthy Dvijotham, M. Pawan Kumar, Robert Stanforth
Recent works have tried to increase the verifiability of adversarially trained networks by running the attacks over domains larger than the original perturbations and adding various regularization terms to the objective.
no code implementations • 14 Apr 2021 • Alessandro De Palma, Rudy Bunel, Alban Desmaison, Krishnamurthy Dvijotham, Pushmeet Kohli, Philip H. S. Torr, M. Pawan Kumar
Finally, we design a BaB framework, named Branch and Dual Network Bound (BaDNB), based on our novel bounding and branching algorithms.
1 code implementation • NeurIPS 2021 • Leonard Berrada, Sumanth Dathathri, Krishnamurthy Dvijotham, Robert Stanforth, Rudy Bunel, Jonathan Uesato, Sven Gowal, M. Pawan Kumar
In this direction, we first introduce a general formulation of probabilistic specifications for neural networks, which captures both probabilistic networks (e. g., Bayesian neural networks, MC-Dropout networks) and uncertain inputs (distributions over inputs arising from sensor noise or other perturbations).
no code implementations • ICLR 2021 • Alessandro De Palma, Harkirat Singh Behl, Rudy Bunel, Philip H. S. Torr, M. Pawan Kumar
Tight and efficient neural network bounding is crucial to the scaling of neural network verification systems.
no code implementations • NeurIPS 2020 • Rudy Bunel, Oliver Hinder, Srinadh Bhojanapalli, Krishnamurthy, Dvijotham
We establish theoretical properties of the nonconvex formulation, showing that it is (almost) free of spurious local minima and has the same global optimum as the convex problem.
2 code implementations • NeurIPS 2020 • Sumanth Dathathri, Krishnamurthy Dvijotham, Alexey Kurakin, aditi raghunathan, Jonathan Uesato, Rudy Bunel, Shreya Shankar, Jacob Steinhardt, Ian Goodfellow, Percy Liang, Pushmeet Kohli
In this work, we propose a first-order dual SDP algorithm that (1) requires memory only linear in the total number of network activations, (2) only requires a fixed number of forward/backward passes through the network per iteration.
no code implementations • 10 Jul 2020 • Jim Winkens, Rudy Bunel, Abhijit Guha Roy, Robert Stanforth, Vivek Natarajan, Joseph R. Ledsam, Patricia MacWilliams, Pushmeet Kohli, Alan Karthikesalingam, Simon Kohl, Taylan Cemgil, S. M. Ali Eslami, Olaf Ronneberger
Reliable detection of out-of-distribution (OOD) inputs is increasingly understood to be a precondition for deployment of machine learning systems.
Ranked #12 on Out-of-Distribution Detection on CIFAR-100 vs CIFAR-10
Out-of-Distribution Detection Out of Distribution (OOD) Detection
2 code implementations • 24 Feb 2020 • Rudy Bunel, Alessandro De Palma, Alban Desmaison, Krishnamurthy Dvijotham, Pushmeet Kohli, Philip H. S. Torr, M. Pawan Kumar
Both the algorithms offer three advantages: (i) they yield bounds that are provably at least as tight as previous dual algorithms relying on Lagrangian relaxations; (ii) they are based on operations analogous to forward/backward pass of neural networks layers and are therefore easily parallelizable, amenable to GPU implementation and able to take advantage of the convolutional structure of problems; and (iii) they allow for anytime stopping while still providing valid bounds.
no code implementations • 14 Sep 2019 • Rudy Bunel, Jingyue Lu, Ilker Turkaslan, Philip H. S. Torr, Pushmeet Kohli, M. Pawan Kumar
We use the data sets to conduct a thorough experimental comparison of existing and new algorithms and to provide an inclusive analysis of the factors impacting the hardness of verification problems.
no code implementations • CVPR 2019 • Chenglong Wang, Rudy Bunel, Krishnamurthy Dvijotham, Po-Sen Huang, Edward Grefenstette, Pushmeet Kohli
This behavior can have severe consequences such as usage of increased computation and induce faults in downstream modules that expect outputs of a certain length.
no code implementations • ICLR 2019 • Chongli Qin, Krishnamurthy, Dvijotham, Brendan O'Donoghue, Rudy Bunel, Robert Stanforth, Sven Gowal, Jonathan Uesato, Grzegorz Swirszcz, Pushmeet Kohli
We show that a number of important properties of interest can be modeled within this class, including conservation of energy in a learned dynamics model of a physical system; semantic consistency of a classifier's output labels under adversarial perturbations and bounding errors in a system that predicts the summation of handwritten digits.
9 code implementations • 30 Oct 2018 • Sven Gowal, Krishnamurthy Dvijotham, Robert Stanforth, Rudy Bunel, Chongli Qin, Jonathan Uesato, Relja Arandjelovic, Timothy Mann, Pushmeet Kohli
Recent work has shown that it is possible to train deep neural networks that are provably robust to norm-bounded adversarial perturbations.
no code implementations • 23 May 2018 • Thomas Joy, Alban Desmaison, Thalaiyasingam Ajanthan, Rudy Bunel, Mathieu Salzmann, Pushmeet Kohli, Philip H. S. Torr, M. Pawan Kumar
The presented algorithms can be applied to any labelling problem using a dense CRF with sparse higher-order potentials.
no code implementations • ICLR 2018 • Rudy Bunel, Matthew Hausknecht, Jacob Devlin, Rishabh Singh, Pushmeet Kohli
Program synthesis is the task of automatically generating a program consistent with a specification.
no code implementations • ICLR 2018 • Rudy Bunel, Ilker Turkaslan, Philip H. S. Torr, Pushmeet Kohli, M. Pawan Kumar
Motivated by the need of accelerating progress in this very important area, we investigate the trade-offs of a number of different approaches based on Mixed Integer Programming, Satisfiability Modulo Theory, as well as a novel method based on the Branch-and-Bound framework.
2 code implementations • NeurIPS 2018 • Rudy Bunel, Ilker Turkaslan, Philip H. S. Torr, Pushmeet Kohli, M. Pawan Kumar
The success of Deep Learning and its potential use in many safety-critical applications has motivated research on formal verification of Neural Network (NN) models.
no code implementations • NeurIPS 2017 • Jacob Devlin, Rudy Bunel, Rishabh Singh, Matthew Hausknecht, Pushmeet Kohli
In our first proposal, portfolio adaptation, a set of induction models is pretrained on a set of related tasks, and the best model is adapted towards the new task using transfer learning.
no code implementations • 4 Dec 2016 • Rudy Bunel, Alban Desmaison, M. Pawan Kumar, Philip H. S. Torr, Pushmeet Kohli
Superoptimization requires the estimation of the best program for a given computational task.
no code implementations • CVPR 2017 • Thalaiyasingam Ajanthan, Alban Desmaison, Rudy Bunel, Mathieu Salzmann, Philip H. S. Torr, M. Pawan Kumar
To this end, we develop a proximal minimization framework, where the dual of each proximal problem is optimized via block coordinate descent.
no code implementations • 6 Nov 2016 • Rudy Bunel, Alban Desmaison, M. Pawan Kumar, Philip H. S. Torr, Pushmeet Kohli
This approach involves repeated sampling of modifications to the program from a proposal distribution, which are accepted or rejected based on whether they preserve correctness, and the improvement they achieve.
no code implementations • 22 Aug 2016 • Alban Desmaison, Rudy Bunel, Pushmeet Kohli, Philip H. S. Torr, M. Pawan Kumar
In contrast to the continuous relaxation-based energy minimisation algorithms used for sparse CRFs, the mean-field algorithm fails to provide strong theoretical guarantees on the quality of its solutions.
1 code implementation • NeurIPS 2016 • Rudy Bunel, Alban Desmaison, Pushmeet Kohli, Philip H. S. Torr, M. Pawan Kumar
We show that it is possible to compile programs written in a low-level language to a differentiable representation.