no code implementations • 19 Sep 2022 • Alicia Y. Tsai, Juliette Decugis, Laurent El Ghaoui, Alper Atamtürk
Implicit models are a general class of learning models that forgo the hierarchical layer structure typical in neural networks and instead define the internal states based on an ``equilibrium'' equation, offering competitive performance and reduced memory consumption.
no code implementations • EMNLP (sustainlp) 2020 • Alicia Y. Tsai, Laurent El Ghaoui
To generate a summary with $k$ sentences, the algorithm only needs to execute $\approx k$ iterations, making it very efficient.
no code implementations • 18 Dec 2021 • Alex Devonport, Forest Yang, Laurent El Ghaoui, Murat Arcak
In addition to applying classical Vapnik-Chervonenkis (VC) dimension bound arguments, we apply the PAC-Bayes theorem by leveraging a formal connection between kernelized empirical inverse Christoffel functions and Gaussian process regression models.
1 code implementation • 8 Sep 2021 • Fangda Gu, He Yin, Laurent El Ghaoui, Murat Arcak, Peter Seiler, Ming Jin
Neural network controllers have become popular in control tasks thanks to their flexibility and expressivity.
no code implementations • 28 Apr 2021 • Alex Devonport, Forest Yang, Laurent El Ghaoui, Murat Arcak
We present an algorithm for data-driven reachability analysis that estimates finite-horizon forward reachable sets for general nonlinear systems using level sets of a certain class of polynomials known as Christoffel functions.
no code implementations • 26 Nov 2020 • Alicia Y. Tsai, Selim Gunay, Minjune Hwang, Pengyuan Zhai, Chenglong Li, Laurent El Ghaoui, Khalid M. Mosalam
Post-hazard reconnaissance for natural disasters (e. g., earthquakes) is important for understanding the performance of the built environment, speeding up the recovery, enhancing resilience and making informed decisions related to current and future hazards.
1 code implementation • NeurIPS 2020 • Fangda Gu, Heng Chang, Wenwu Zhu, Somayeh Sojoudi, Laurent El Ghaoui
Graph Neural Networks (GNNs) are widely used deep learning models that learn meaningful representations from graph-structured data.
1 code implementation • 15 Jun 2020 • Armin Askari, Quentin Rebjock, Alexandre d'Aspremont, Laurent El Ghaoui
We describe a series of algorithms that efficiently implement Gaussian model-X knockoffs to control the false discovery rate on large scale feature selection problems.
1 code implementation • ICML 2020 • Geoffrey Négiar, Gideon Dresdner, Alicia Tsai, Laurent El Ghaoui, Francesco Locatello, Robert M. Freund, Fabian Pedregosa
We propose a novel Stochastic Frank-Wolfe (a. k. a.
no code implementations • 17 Aug 2019 • Laurent El Ghaoui, Fangda Gu, Bertrand Travacca, Armin Askari, Alicia Y. Tsai
Implicit deep learning prediction rules generalize the recursive rules of feedforward neural networks.
no code implementations • 23 May 2019 • Armin Askari, Alexandre d'Aspremont, Laurent El Ghaoui
We propose a sparse version of naive Bayes, which can be used for feature selection.
8 code implementations • 24 Jan 2019 • Hongyang Zhang, Yaodong Yu, Jiantao Jiao, Eric P. Xing, Laurent El Ghaoui, Michael. I. Jordan
We identify a trade-off between robustness and accuracy that serves as a guiding principle in the design of defenses against adversarial examples.
Ranked #3 on Adversarial Attack on CIFAR-10
1 code implementation • 20 Nov 2018 • Fangda Gu, Armin Askari, Laurent El Ghaoui
In this paper, we introduce a new class of lifted models, Fenchel lifted networks, that enjoy the same benefits as previous lifted models, without suffering a degradation in performance over classical networks.
2 code implementations • 6 Nov 2018 • Gary Cheng, Armin Askari, Kannan Ramchandran, Laurent El Ghaoui
In this paper, we consider the problem of selecting representatives from a data set for arbitrary supervised/unsupervised learning tasks.
no code implementations • 18 Jun 2018 • Armin Askari, Forest Yang, Laurent El Ghaoui
Outlier detection methods have become increasingly relevant in recent years due to increased security concerns and because of its vast application to different fields.
no code implementations • 3 May 2018 • Armin Askari, Geoffrey Negiar, Rajiv Sambharya, Laurent El Ghaoui
We describe a novel family of models of multi- layer feedforward neural networks in which the activation functions are encoded via penalties in the training problem.
no code implementations • 30 Oct 2014 • Vu Pham, Laurent El Ghaoui, Arturo Fernandez
Many learning tasks, such as cross-validation, parameter search, or leave-one-out analysis, involve multiple instances of similar problems, each instance sharing a large part of learning data with the others.
no code implementations • 29 Apr 2014 • Jinzhu Jia, Luke Miratrix, Bin Yu, Brian Gawalt, Laurent El Ghaoui, Luke Barnesmoore, Sophie Clavier
In this paper we propose a general framework for topic-specific summarization of large text corpora and illustrate how it can be used for the analysis of news databases.