Search Results for author:
Found 9 papers, 4 papers with code
Expressive Losses for Verified Robustness via Convex Combinations
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.
IBP Regularization for Verified Adversarial Robustness via Branch-and-Bound
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.
In Defense of the Unitary Scalarization for Deep Multi-Task Learning
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.
Improved Branch and Bound for Neural Network Verification via Lagrangian Decomposition
Finally, we design a BaB framework, named Branch and Dual Network Bound (BaDNB), based on our novel bounding and branching algorithms.
Scaling the Convex Barrier with Sparse Dual Algorithms
Tight and efficient neural network bounding is crucial to the scaling of neural network verification systems.
Lagrangian Decomposition for Neural Network Verification
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.
Sampling Acquisition Functions for Batch Bayesian Optimization
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.
Benchmarking and Optimization of Gradient Boosting Decision Tree Algorithms
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.
Distributed Stratified Locality Sensitive Hashing for Critical Event Prediction in the Cloud
The availability of massive healthcare data repositories calls for efficient tools for data-driven medicine.
