activity
20152019
most citedRecurrent Neural Networks in the Eye of Differential Equations

23 citations · 47 across the 5 of their papers we have counts for

collaborators

6 papers

cs.LG201923 cited

Recurrent Neural Networks in the Eye of Differential Equations

Murphy Yuezhen Niu, Lior Horesh, Isaac Chuang

To understand the fundamental trade-offs between training stability, temporal dynamics and architectural complexity of recurrent neural networks~(RNNs), we directly analyze RNN arc…

stat.ML201714 cited

Globally Optimal Symbolic Regression

Vernon Austel, Sanjeeb Dash, Oktay Gunluk +4

In this study we introduce a new technique for symbolic regression that guarantees global optimality. This is achieved by formulating a mixed integer non-linear program (MINLP) who…

stat.ML20179 cited

Should You Derive, Or Let the Data Drive? An Optimization Framework for Hybrid First-Principles Data-Driven Modeling

Remi R. Lam, Lior Horesh, Haim Avron +1

Mathematical models are used extensively for diverse tasks including analysis, optimization, and decision making. Frequently, those models are principled but imperfect representati…

stat.ML2017

Image classification using local tensor singular value decompositions

Elizabeth Newman, Misha Kilmer, Lior Horesh

From linear classifiers to neural networks, image classification has been a widely explored topic in mathematics, and many algorithms have proven to be effective classifiers. Howev…

stat.ML20171 cited

Experimental Design for Non-Parametric Correction of Misspecified Dynamical Models

Gal Shulkind, Lior Horesh, Haim Avron

We consider a class of misspecified dynamical models where the governing term is only approximately known. Under the assumption that observations of the system's evolution are acce…

math.OC2015

General Optimization Framework for Robust and Regularized 3D Full Waveform Inversion

Stephen Becker, Lior Horesh, Aleksandr Aravkin +1

Scarcity of hydrocarbon resources and high exploration risks motivate the development of high fidelity algorithms and computationally viable approaches to exploratory geophysics. W…