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.
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.
1 code implementation • 11 Jan 2022 • Vitaly Kurin, Alessandro De Palma, Ilya Kostrikov, Shimon Whiteson, M. Pawan Kumar
We show that unitary scalarization, coupled with standard regularization and stabilization techniques from single-task learning, matches or improves upon the performance of complex multi-task optimizers in popular supervised and reinforcement learning settings.
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.
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.
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 • 22 Mar 2019 • Alessandro De Palma, Celestine Mendler-Dünner, Thomas Parnell, Andreea Anghel, Haralampos Pozidis
We present Acquisition Thompson Sampling (ATS), a novel technique for batch Bayesian Optimization (BO) based on the idea of sampling multiple acquisition functions from a stochastic process.
no code implementations • 12 Sep 2018 • Andreea Anghel, Nikolaos Papandreou, Thomas Parnell, Alessandro De Palma, Haralampos Pozidis
Gradient boosting decision trees (GBDTs) have seen widespread adoption in academia, industry and competitive data science due to their state-of-the-art performance in many machine learning tasks.
no code implementations • 1 Dec 2017 • Alessandro De Palma, Erik Hemberg, Una-May O'Reilly
The availability of massive healthcare data repositories calls for efficient tools for data-driven medicine.