Bilevel Programs Meet Deep Learning: A Unifying View on Inference
Learning Methods

v1v2 (latest)

Bilevel Programs Meet Deep Learning: A Unifying View on Inference Learning Methods

15 May 2021

Christopher Zach

ArXiv (abs)PDF HTML

Papers citing "Bilevel Programs Meet Deep Learning: A Unifying View on Inference Learning Methods"

12 / 12 papers shown

Title
Predictive Coding Approximates Backprop along Arbitrary Computation Graphs Beren Millidge Alexander Tschantz Christopher L. Buckley 70 122 0 07 Jun 2020
Optimizing Millions of Hyperparameters by Implicit Differentiation Jonathan Lorraine Paul Vicol David Duvenaud DD 114 415 0 06 Nov 2019
Deep Declarative Networks: A New Hope Stephen Gould Leonid Sigal Dylan Campbell AI4CE 71 105 0 11 Sep 2019
Meta-Learning with Implicit Gradients Aravind Rajeswaran Chelsea Finn Sham Kakade Sergey Levine 110 855 0 10 Sep 2019
Fenchel Lifted Networks: A Lagrange Relaxation of Neural Network Training Fangda Gu Armin Askari L. Ghaoui 55 39 0 20 Nov 2018
Lifted Proximal Operator Machines Jia Li Cong Fang Zhouchen Lin ODL 50 36 0 05 Nov 2018
Bilevel Programming for Hyperparameter Optimization and Meta-Learning Luca Franceschi P. Frasconi Saverio Salzo Riccardo Grazzi Massimiliano Pontil 176 728 0 13 Jun 2018
Convergent Block Coordinate Descent for Training Tikhonov Regularized Deep Neural Networks Ziming Zhang M. Brand 43 71 0 20 Nov 2017
Towards Biologically Plausible Deep Learning Yoshua Bengio Dong-Hyun Lee J. Bornschein Thomas Mesnard Zhouhan Lin DRL OOD 67 351 0 14 Feb 2015
Difference Target Propagation Dong-Hyun Lee Saizheng Zhang Asja Fischer Yoshua Bengio AAML 93 350 0 23 Dec 2014
How Auto-Encoders Could Provide Credit Assignment in Deep Networks via Target Propagation Yoshua Bengio 98 184 0 29 Jul 2014
Task-Driven Dictionary Learning Julien Mairal Francis R. Bach Jean Ponce 99 898 0 27 Sep 2010

We use cookies and other tracking technologies to improve your browsing experience on our website, to show you personalized content and targeted ads, to analyze our website traffic, and to understand where our visitors are coming from. See our policy.