AIConfPaper
← Search

Ross Anderson

6 accepted papers

2022

Constrained Discrete Black-Box Optimization using Mixed-Integer Programming

Theodore P Papalexopoulos, Christian Tjandraatmadja, Ross Anderson, Juan Pablo Vielma, David Belanger
ICML 2022spotlight

Discrete black-box optimization problems are challenging for model-based optimization (MBO) algorithms, such as Bayesian optimization, due to the size of the search space and the need to satisfy combinatorial constraints. In particular, these methods require repeatedly solving a complex discrete glo…

Cited by 35Source ↗PDF ↗code ↗Scholar ↗
2021

Manipulating SGD with Data Ordering Attacks

I Shumailov, Zakhar Shumaylov, Dmitry Kazhdan, Yiren Zhao, Nicolas Papernot, Murat A Erdogdu +1
NeurIPS 2021poster

Machine learning is vulnerable to a wide variety of attacks. It is now well understood that by changing the underlying data distribution, an adversary can poison the model trained with it or introduce backdoors. In this paper we present a novel class of training-time attacks that require no changes…

Cited by 102Source ↗PDF ↗Scholar ↗
2021

Markpainting: Adversarial Machine Learning meets Inpainting

David Khachaturov, Ilia Shumailov, Yiren Zhao, Nicolas Papernot, Ross Anderson
ICML 2021spotlight

Inpainting is a learned interpolation technique that is based on generative modeling and used to populate masked or missing pieces in an image; it has wide applications in picture editing and retouching. Recently, inpainting started being used for watermark removal, raising concerns. In this paper w…

Cited by 12Source ↗PDF ↗code ↗Scholar ↗
2020

CAQL: Continuous Action Q-Learning

Moonkyung Ryu, Yinlam Chow, Ross Anderson, Christian Tjandraatmadja, Craig Boutilier
ICLR 2020poster

Reinforcement learning (RL) with value-based methods (e.g., Q-learning) has shown success in a variety of domains such as games and recommender systems (RSs). When the action space is finite, these algorithms implicitly finds a policy by learning the optimal value function, which are often very effi…

Cited by 62Source ↗Scholar ↗
2020

Reinforcement Learning with Combinatorial Actions: An Application to Vehicle Routing

Arthur Delarue, Ross Anderson, Christian Tjandraatmadja
NeurIPS 2020poster

Value-function-based methods have long played an important role in reinforcement learning. However, finding the best next action given a value function of arbitrary complexity is nontrivial when the action space is too large for enumeration. We develop a framework for value-function-based deep reinf…

Cited by 143Source ↗PDF ↗code ↗Scholar ↗
2020

The Convex Relaxation Barrier, Revisited: Tightened Single-Neuron Relaxations for Neural Network Verification

Christian Tjandraatmadja, Ross Anderson, Joey Huchette, Will Ma, KRUNAL KISHOR PATEL, Juan Pablo Vielma
NeurIPS 2020poster

We improve the effectiveness of propagation- and linear-optimization-based neural network verification algorithms with a new tightened convex relaxation for ReLU neurons. Unlike previous single-neuron relaxations which focus only on the univariate input space of the ReLU, our method considers the mu…

Cited by 103Source ↗PDF ↗code ↗Scholar ↗