An Optimal Control Approach to Deep Learning and Applications to Discrete-Weight Neural Networks

4 March 2018

Papers citing "An Optimal Control Approach to Deep Learning and Applications to Discrete-Weight Neural Networks"

40 / 40 papers shown

Title
Data Selection via Optimal Control for Language Models Yuxian Gu Li Dong Hongning Wang Y. Hao Qingxiu Dong Furu Wei Minlie Huang AI4CE 58 5 0 09 Oct 2024
Online Control-Informed Learning Zihao Liang Tianyu Zhou Zehui Lu Shaoshuai Mou 33 1 0 04 Oct 2024
Unified Universality Theorem for Deep and Shallow Joint-Group-Equivariant Machines Sho Sonoda Yuka Hashimoto Isao Ishikawa Masahiro Ikeda 39 0 0 22 May 2024
Neural Dynamic Data Valuation Zhangyong Liang Huanhuan Gao Ji Zhang TDI 48 1 0 30 Apr 2024
PID Control-Based Self-Healing to Improve the Robustness of Large Language Models Zhuotong Chen Zihu Wang Yifan Yang Qianxiao Li Zheng Zhang AAML 42 1 0 31 Mar 2024
Asymptotically Fair Participation in Machine Learning Models: an Optimal Control Perspective Zhuotong Chen Qianxiao Li Zheng Zhang FaML 17 1 0 16 Nov 2023
Deep Ridgelet Transform: Voice with Koopman Operator Proves Universality of Formal Deep Networks Sho Sonoda Yuka Hashimoto Isao Ishikawa Masahiro Ikeda 27 3 0 05 Oct 2023
Neural Delay Differential Equations: System Reconstruction and Image Classification Qunxi Zhu Yao Guo Wei Lin 25 32 0 11 Apr 2023
Deep Generalized Schrödinger Bridge Guan-Horng Liu T. Chen Oswin So Evangelos A. Theodorou OT AI4CE 16 35 0 20 Sep 2022
An Optimal Control Method to Compute the Most Likely Transition Path for Stochastic Dynamical Systems with Jumps Wei Wei Ting Gao Jinqiao Duan Xiaoli Chen 16 12 0 31 Mar 2022
Neural Piecewise-Constant Delay Differential Equations Qunxi Zhu Yifei Shen Dongsheng Li Wei-Jer Lin PINN 30 6 0 04 Jan 2022
Likelihood Training of Schrödinger Bridge using Forward-Backward SDEs Theory T. Chen Guan-Horng Liu Evangelos A. Theodorou DiffM OT 174 165 0 21 Oct 2021
An Optimal Control Framework for Joint-channel Parallel MRI Reconstruction without Coil Sensitivities Wanyu Bian Yunmei Chen X. Ye 44 16 0 20 Sep 2021
Dynamic Game Theoretic Neural Optimizer Guan-Horng Liu T. Chen Evangelos A. Theodorou AI4CE 8 4 0 08 May 2021
Diffusion Mechanism in Residual Neural Network: Theory and Applications Tangjun Wang Zehao Dou Chenglong Bao Zuoqiang Shi DiffM 22 7 0 07 May 2021
Personalized Algorithm Generation: A Case Study in Learning ODE Integrators Yue Guo Felix Dietrich Tom S. Bertalan Danimir T. Doncevic Manuel Dahmen Ioannis G. Kevrekidis Qianxiao Li 22 11 0 04 May 2021
Optimal sequential decision making with probabilistic digital twins C. Agrell Kristina Rognlien Dahl A. Hafver 21 7 0 12 Mar 2021
Amata: An Annealing Mechanism for Adversarial Training Acceleration Nanyang Ye Qianxiao Li Xiao-Yun Zhou Zhanxing Zhu AAML 32 15 0 15 Dec 2020
Machine Learning and Computational Mathematics Weinan E PINN AI4CE 34 61 0 23 Sep 2020
Continuous-in-Depth Neural Networks A. Queiruga N. Benjamin Erichson D. Taylor Michael W. Mahoney 18 46 0 05 Aug 2020
A Differential Game Theoretic Neural Optimizer for Training Residual Networks Guan-Horng Liu T. Chen Evangelos A. Theodorou 24 2 0 17 Jul 2020
Machine Learning and Control Theory A. Bensoussan Yiqun Li Dinh Phan Cao Nguyen M. Tran S. Yam Xiang Zhou AI4CE 32 12 0 10 Jun 2020
Structure preserving deep learning E. Celledoni Matthias Joachim Ehrhardt Christian Etmann R. McLachlan B. Owren Carola-Bibiane Schönlieb Ferdia Sherry AI4CE 15 44 0 05 Jun 2020
Robust Deep Learning as Optimal Control: Insights and Convergence Guarantees Jacob H. Seidman Mahyar Fazlyab V. Preciado George J. Pappas AAML 22 15 0 01 May 2020
A Mean-field Analysis of Deep ResNet and Beyond: Towards Provable Optimization Via Overparameterization From Depth Yiping Lu Chao Ma Yulong Lu Jianfeng Lu Lexing Ying MLT 39 78 0 11 Mar 2020
DDPNOpt: Differential Dynamic Programming Neural Optimizer Guan-Horng Liu T. Chen Evangelos A. Theodorou 27 7 0 20 Feb 2020
Total Deep Variation for Linear Inverse Problems Erich Kobler Alexander Effland K. Kunisch Thomas Pock 19 89 0 14 Jan 2020
Pontryagin Differentiable Programming: An End-to-End Learning and Control Framework Wanxin Jin Zhaoran Wang Zhuoran Yang Shaoshuai Mou 30 77 0 30 Dec 2019
Deep Learning via Dynamical Systems: An Approximation Perspective Qianxiao Li Ting Lin Zuowei Shen AI4TS AI4CE 25 107 0 22 Dec 2019
Dynamical System Inspired Adaptive Time Stepping Controller for Residual Network Families Yibo Yang Jianlong Wu Hongyang Li Xia Li Tiancheng Shen Zhouchen Lin OOD 16 21 0 23 Nov 2019
Review: Ordinary Differential Equations For Deep Learning Xinshi Chen AI4TS AI4CE 24 5 0 01 Nov 2019
Deep Learning Theory Review: An Optimal Control and Dynamical Systems Perspective Guan-Horng Liu Evangelos A. Theodorou AI4CE 24 71 0 28 Aug 2019
An Optimal Control Approach to Early Stopping Variational Methods for Image Restoration Alexander Effland Erich Kobler K. Kunisch Thomas Pock 21 3 0 19 Jul 2019
Distributed Optimization for Over-Parameterized Learning Chi Zhang Qianxiao Li 24 4 0 14 Jun 2019
You Only Propagate Once: Accelerating Adversarial Training via Maximal Principle Dinghuai Zhang Tianyuan Zhang Yiping Lu Zhanxing Zhu Bin Dong AAML 34 357 0 02 May 2019
Deep learning as optimal control problems: models and numerical methods Martin Benning E. Celledoni Matthias Joachim Ehrhardt B. Owren Carola-Bibiane Schönlieb 19 81 0 11 Apr 2019
Understanding Straight-Through Estimator in Training Activation Quantized Neural Nets Penghang Yin J. Lyu Shuai Zhang Stanley Osher Y. Qi Jack Xin MQ LLMSV 21 308 0 13 Mar 2019
A Mean-Field Optimal Control Formulation of Deep Learning Weinan E Jiequn Han Qianxiao Li OOD 14 182 0 03 Jul 2018
A Proximal Stochastic Gradient Method with Progressive Variance Reduction Lin Xiao Tong Zhang ODL 93 737 0 19 Mar 2014
Stochastic Gradient Descent for Non-smooth Optimization: Convergence Results and Optimal Averaging Schemes Ohad Shamir Tong Zhang 104 572 0 08 Dec 2012