59 citations · 124 across the 11 of their papers we have counts for
12 papers
Augmenting Interpretable Models with LLMs during Training
Chandan Singh, Armin Askari, Rich Caruana +1
Recent large language models (LLMs) have demonstrated remarkable prediction performance for a growing array of tasks. However, their proliferation into high-stakes domains (e.g. me…
Approximation Bounds for Sparse Programs
Armin Askari, Alexandre d'Aspremont, Laurent El Ghaoui
We show that sparsity constrained optimization problems over low dimensional spaces tend to have a small duality gap. We use the Shapley-Folkman theorem to derive both data-driven…
FANOK: Knockoffs in Linear Time
Armin Askari, Quentin Rebjock, Alexandre d'Aspremont +1
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. Identifying…
Implicit Deep Learning
Laurent El Ghaoui, Fangda Gu, Bertrand Travacca +2
Implicit deep learning prediction rules generalize the recursive rules of feedforward neural networks. Such rules are based on the solution of a fixed-point equation involving a si…
Naive Feature Selection: a Nearly Tight Convex Relaxation for Sparse Naive Bayes
Armin Askari, Alexandre d'Aspremont, Laurent El Ghaoui
Due to its linear complexity, naive Bayes classification remains an attractive supervised learning method, especially in very large-scale settings. We propose a sparse version of n…
Fenchel Lifted Networks: A Lagrange Relaxation of Neural Network Training
Fangda Gu, Armin Askari, Laurent El Ghaoui
Despite the recent successes of deep neural networks, the corresponding training problem remains highly non-convex and difficult to optimize. Classes of models have been proposed t…