1 code implementation • 27 Jan 2023 • Valentina Zantedeschi, Luca Franceschi, Jean Kaddour, Matt J. Kusner, Vlad Niculae
We propose a continuous optimization framework for discovering a latent directed acyclic graph (DAG) from observational data.
no code implementations • 21 Dec 2022 • Ibrahim Alabdulmohsin, Nicole Chiou, Alexander D'Amour, Arthur Gretton, Sanmi Koyejo, Matt J. Kusner, Stephen R. Pfohl, Olawale Salaudeen, Jessica Schrouff, Katherine Tsai
We show that the optimal target predictor can be non-parametrically identified with the help of concept and proxy variables available only in the source domain, and unlabeled data from the target.
no code implementations • 30 Jun 2022 • Jean Kaddour, Aengus Lynch, Qi Liu, Matt J. Kusner, Ricardo Silva
Causal Machine Learning (CausalML) is an umbrella term for machine learning methods that formalize the data-generation process as a structural causal model (SCM).
1 code implementation • 1 Feb 2022 • Jean Kaddour, Linqing Liu, Ricardo Silva, Matt J. Kusner
Recently, flat-minima optimizers, which seek to find parameters in low-loss neighborhoods, have been shown to improve a neural network's generalization performance over stochastic and adaptive gradient-based optimizers.
1 code implementation • 28 Jan 2022 • Natalie Maus, Haydn T. Jones, Juston S. Moore, Matt J. Kusner, John Bradshaw, Jacob R. Gardner
By reformulating the encoder to function as both an encoder for the DAE globally and as a deep kernel for the surrogate model within a trust region, we better align the notion of local optimization in the latent space with local optimization in the input space.
no code implementations • 15 Sep 2021 • Nitin Agrawal, James Bell, Adrià Gascón, Matt J. Kusner
We address the problem of efficiently verifying a commitment in a two-party computation.
1 code implementation • 9 Jun 2021 • Limor Gultchin, David S. Watson, Matt J. Kusner, Ricardo Silva
We examine the problem of causal response estimation for complex objects (e. g., text, images, genomics).
2 code implementations • NeurIPS 2021 • Jean Kaddour, Yuchen Zhu, Qi Liu, Matt J. Kusner, Ricardo Silva
We address the estimation of conditional average treatment effects (CATEs) for structured treatments (e. g., graphs, images, texts).
2 code implementations • 10 May 2021 • Afsaneh Mastouri, Yuchen Zhu, Limor Gultchin, Anna Korba, Ricardo Silva, Matt J. Kusner, Arthur Gretton, Krikamol Muandet
In particular, we provide a unifying view of two-stage and moment restriction approaches for solving this problem in a nonlinear setting.
1 code implementation • NeurIPS 2020 • John Bradshaw, Brooks Paige, Matt J. Kusner, Marwin H. S. Segler, José Miguel Hernández-Lobato
When designing new molecules with particular properties, it is not only important what to make but crucially how to make it.
1 code implementation • 9 Oct 2020 • Valentina Zantedeschi, Matt J. Kusner, Vlad Niculae
We address the problem of learning binary decision trees that partition data for some downstream task.
1 code implementation • NeurIPS 2020 • Niki Kilbertus, Matt J. Kusner, Ricardo Silva
Causal treatment effect estimation is a key problem that arises in a variety of real-world settings, from personalized medicine to governmental policy making.
no code implementations • 16 Mar 2020 • Qi Liu, Matt J. Kusner, Phil Blunsom
Contextual embeddings, such as ELMo and BERT, move beyond global word representations like Word2Vec and achieve ground-breaking performance on a wide range of natural language processing tasks.
1 code implementation • 3 Mar 2020 • Limor Gultchin, Matt J. Kusner, Varun Kanade, Ricardo Silva
Discovering the causal effect of a decision is critical to nearly all forms of decision-making.
1 code implementation • 5 Nov 2019 • Valentina Zantedeschi, Fabrizio Falasca, Alyson Douglas, Richard Strange, Matt J. Kusner, Duncan Watson-Parris
One of the greatest sources of uncertainty in future climate projections comes from limitations in modelling clouds and in understanding how different cloud types interact with the climate system.
no code implementations • 8 Jul 2019 • Nitin Agrawal, Ali Shahin Shamsabadi, Matt J. Kusner, Adrià Gascón
In this work, we investigate the advantages of designing training algorithms alongside a novel secure protocol, incorporating optimizations on both fronts.
1 code implementation • 1 Jul 2019 • Niki Kilbertus, Philip J. Ball, Matt J. Kusner, Adrian Weller, Ricardo Silva
We demonstrate our new sensitivity analysis tools in real-world fairness scenarios to assess the bias arising from confounding.
1 code implementation • NeurIPS 2019 • John Bradshaw, Brooks Paige, Matt J. Kusner, Marwin H. S. Segler, José Miguel Hernández-Lobato
Deep generative models are able to suggest new organic molecules by generating strings, trees, and graphs representing their structure.
no code implementations • ICLR Workshop DeepGenStruct 2019 • John Bradshaw, Matt J. Kusner, Brooks Paige, Marwin H. S. Segler, José Miguel Hernández-Lobato
We therefore propose a new molecule generation model, mirroring a more realistic real-world process, where reactants are selected and combined to form more complex molecules.
no code implementations • 13 Jan 2019 • Zhixiang Eddie Xu, Matt J. Kusner, Kilian Q. Weinberger, Alice X. Zheng
As machine learning transitions increasingly towards real world applications controlling the test-time cost of algorithms becomes more and more crucial.
1 code implementation • ICML 2018 • Amartya Sanyal, Matt J. Kusner, Adrià Gascón, Varun Kanade
The main drawback of using fully homomorphic encryption is the amount of time required to evaluate large machine learning models on encrypted data.
1 code implementation • ICML 2018 • Niki Kilbertus, Adrià Gascón, Matt J. Kusner, Michael Veale, Krishna P. Gummadi, Adrian Weller
Recent work has explored how to train machine learning models which do not discriminate against any subgroup of the population as determined by sensitive attributes such as gender or race.
no code implementations • 6 Jun 2018 • Matt J. Kusner, Chris Russell, Joshua R. Loftus, Ricardo Silva
Most approaches in algorithmic fairness constrain machine learning methods so the resulting predictions satisfy one of several intuitive notions of fairness.
no code implementations • ICLR 2019 • John Bradshaw, Matt J. Kusner, Brooks Paige, Marwin H. S. Segler, José Miguel Hernández-Lobato
Chemical reactions can be described as the stepwise redistribution of electrons in molecules.
no code implementations • 15 May 2018 • Joshua R. Loftus, Chris Russell, Matt J. Kusner, Ricardo Silva
In this work, we argue for the importance of causal reasoning in creating fair algorithms for decision making.
1 code implementation • ICLR 2018 • David Janz, Jos van der Westhuizen, Brooks Paige, Matt J. Kusner, José Miguel Hernández-Lobato
This validator provides insight as to how individual sequence elements influence the validity of the overall sequence, and can be used to constrain sequence based models to generate valid sequences -- and thus faithfully model discrete objects.
no code implementations • NeurIPS 2017 • Chris Russell, Matt J. Kusner, Joshua Loftus, Ricardo Silva
In this paper, we show how it is possible to make predictions that are approximately fair with respect to multiple possible causal models at once, thus mitigating the problem of exact causal specification.
2 code implementations • NeurIPS 2017 • Matt J. Kusner, Joshua R. Loftus, Chris Russell, Ricardo Silva
Machine learning can impact people with legal or ethical consequences when it is used to automate decisions in areas such as insurance, lending, hiring, and predictive policing.
3 code implementations • ICML 2017 • Matt J. Kusner, Brooks Paige, José Miguel Hernández-Lobato
Crucially, state-of-the-art methods often produce outputs that are not valid.
1 code implementation • NeurIPS 2016 • Gao Huang, Chuan Guo, Matt J. Kusner, Yu Sun, Fei Sha, Kilian Q. Weinberger
Accurately measuring the similarity between text documents lies at the core of many real world applications of machine learning.
no code implementations • 12 Nov 2016 • Matt J. Kusner, José Miguel Hernández-Lobato
Generative Adversarial Networks (GAN) have limitations when the goal is to generate sequences of discrete elements.
no code implementations • 17 Dec 2015 • Matt J. Kusner, Yu Sun, Karthik Sridharan, Kilian Q. Weinberger
Causal inference has the potential to have significant impact on medical research, prevention and control of diseases, and identifying factors that impact economic changes to name just a few.
no code implementations • NeurIPS 2015 • Gustavo Malkomes, Matt J. Kusner, Wenlin Chen, Kilian Q. Weinberger, Benjamin Moseley
Clustering large data is a fundamental problem with a vast number of applications.
no code implementations • 19 Nov 2015 • Jacob R. Gardner, Paul Upchurch, Matt J. Kusner, Yixuan Li, Kilian Q. Weinberger, Kavita Bala, John E. Hopcroft
Many tasks in computer vision can be cast as a "label changing" problem, where the goal is to make a semantic change to the appearance of an image or some subject in an image in order to alter the class membership.
no code implementations • 16 Jan 2015 • Matt J. Kusner, Jacob R. Gardner, Roman Garnett, Kilian Q. Weinberger
The success of machine learning has led practitioners in diverse real-world settings to learn classifiers for practical problems.
no code implementations • 4 Dec 2014 • Matt J. Kusner, Nicholas I. Kolkin, Stephen Tyree, Kilian Q. Weinberger
Specifically, we show that we can reduce data sets to 16% and in some cases as little as 2% of their original size, while approximately matching the test error of kNN classification on the full training set.
no code implementations • 9 Oct 2012 • Zhixiang Xu, Matt J. Kusner, Kilian Q. Weinberger, Minmin Chen
Recently, machine learning algorithms have successfully entered large-scale real-world industrial applications (e. g. search engines and email spam filters).