Skip to yearly menu bar Skip to main content


(23 events)   Timezone: America/Los_Angeles  
Show all
Toggle Poster Visibility
Poster
Tue Dec 10 10:45 AM -- 12:45 PM (PST) @ East Exhibition Hall B + C #135
An Improved Analysis of Training Over-parameterized Deep Neural Networks
In Deep Learning -- Optimization for Deep Networks
Difan Zou · Quanquan Gu
[ Paper]  [ Poster] 
Poster
Tue Dec 10 10:45 AM -- 12:45 PM (PST) @ East Exhibition Hall B + C #136
Controlling Neural Level Sets
In Deep Learning -- Optimization for Deep Networks
Matan Atzmon · Niv Haim · Lior Yariv · Ofer Israelov · Haggai Maron · Yaron Lipman
[ Paper]  [ Poster] 
Poster
Tue Dec 10 10:45 AM -- 12:45 PM (PST) @ East Exhibition Hall B + C #137
Deep Equilibrium Models
In Deep Learning -- Optimization for Deep Networks
Shaojie Bai · J. Zico Kolter · Vladlen Koltun
[ Paper]  [ Poster]  [ Slides] 
Poster
Tue Dec 10 10:45 AM -- 12:45 PM (PST) @ East Exhibition Hall B + C #138
Differentiable Cloth Simulation for Inverse Problems
In Deep Learning -- Optimization for Deep Networks
Junbang Liang · Ming Lin · Vladlen Koltun
Poster
Tue Dec 10 10:45 AM -- 12:45 PM (PST) @ East Exhibition Hall B + C #139
Efficient and Accurate Estimation of Lipschitz Constants for Deep Neural Networks
In Deep Learning -- Optimization for Deep Networks
Mahyar Fazlyab · Alexander Robey · Hamed Hassani · Manfred Morari · George J. Pappas
[ Paper]  [ Slides] 
Poster
Tue Dec 10 10:45 AM -- 12:45 PM (PST) @ East Exhibition Hall B + C #140
Fine-grained Optimization of Deep Neural Networks
In Deep Learning -- Optimization for Deep Networks
Mete Ozay
[ Paper]  [ Poster] 
Poster
Tue Dec 10 10:45 AM -- 12:45 PM (PST) @ East Exhibition Hall B + C #141
Generalization Bounds of Stochastic Gradient Descent for Wide and Deep Neural Networks
In Deep Learning -- Optimization for Deep Networks
Yuan Cao · Quanquan Gu
[ Paper]  [ Slides] 
Poster
Tue Dec 10 10:45 AM -- 12:45 PM (PST) @ East Exhibition Hall B + C #142
On Learning Over-parameterized Neural Networks: A Functional Approximation Perspective
In Deep Learning -- Optimization for Deep Networks
Lili Su · Pengkun Yang
[ Paper]  [ Poster] 
Poster
Tue Dec 10 10:45 AM -- 12:45 PM (PST) @ East Exhibition Hall B + C #143
Stagewise Training Accelerates Convergence of Testing Error Over SGD
In Deep Learning -- Optimization for Deep Networks
Zhuoning Yuan · Yan Yan · Rong Jin · Tianbao Yang
[ Paper]  [ Slides] 
Poster
Tue Dec 10 10:45 AM -- 12:45 PM (PST) @ East Exhibition Hall B + C #144
Towards Explaining the Regularization Effect of Initial Large Learning Rate in Training Neural Networks
In Deep Learning -- Optimization for Deep Networks
Yuanzhi Li · Colin Wei · Tengyu Ma
[ Paper]  [ Slides] 
Poster
Tue Dec 10 10:45 AM -- 12:45 PM (PST) @ East Exhibition Hall B + C #145
You Only Propagate Once: Accelerating Adversarial Training via Maximal Principle
In Deep Learning -- Optimization for Deep Networks
Dinghuai Zhang · Tianyuan Zhang · Yiping Lu · Zhanxing Zhu · Bin Dong
[ Paper]  [ Poster] 
Poster
Tue Dec 10 05:30 PM -- 07:30 PM (PST) @ East Exhibition Hall B + C #88
Constrained deep neural network architecture search for IoT devices accounting for hardware calibration
In Deep Learning -- Optimization for Deep Networks
Florian Scheidegger · Luca Benini · Costas Bekas · A. Cristiano I. Malossi
[ Paper]  [ Poster] 
Poster
Tue Dec 10 05:30 PM -- 07:30 PM (PST) @ East Exhibition Hall B + C #89
Implicit Regularization of Discrete Gradient Dynamics in Linear Neural Networks
In Deep Learning -- Optimization for Deep Networks
Gauthier Gidel · Francis Bach · Simon Lacoste-Julien
[ Paper]  [ Poster] 
Poster
Tue Dec 10 05:30 PM -- 07:30 PM (PST) @ East Exhibition Hall B + C #90
In-Place Zero-Space Memory Protection for CNN
In Deep Learning -- Optimization for Deep Networks
Hui Guan · Lin Ning · Zhen Lin · Xipeng Shen · Huiyang Zhou · Seung-Hwan Lim
[ Paper]  [ Poster] 
Poster
Tue Dec 10 05:30 PM -- 07:30 PM (PST) @ East Exhibition Hall B + C #91
Large Scale Structure of Neural Network Loss Landscapes
In Deep Learning -- Optimization for Deep Networks
Stanislav Fort · Stanislaw Jastrzebski
[ Paper]  [ Poster] 
Poster
Tue Dec 10 05:30 PM -- 07:30 PM (PST) @ East Exhibition Hall B + C #92
Learning and Generalization in Overparameterized Neural Networks, Going Beyond Two Layers
In Deep Learning -- Optimization for Deep Networks
Zeyuan Allen-Zhu · Yuanzhi Li · Yingyu Liang
[ Paper]  [ Slides] 
Poster
Tue Dec 10 05:30 PM -- 07:30 PM (PST) @ East Exhibition Hall B + C #93
Limitations of the empirical Fisher approximation for natural gradient descent
In Deep Learning -- Optimization for Deep Networks
Frederik Kunstner · Philipp Hennig · Lukas Balles
Poster
Tue Dec 10 05:30 PM -- 07:30 PM (PST) @ East Exhibition Hall B + C #94
Maximum Mean Discrepancy Gradient Flow
In Deep Learning -- Optimization for Deep Networks
Michael Arbel · Anna Korba · Adil Salim · Arthur Gretton
Poster
Tue Dec 10 05:30 PM -- 07:30 PM (PST) @ East Exhibition Hall B + C #95
On Lazy Training in Differentiable Programming
In Deep Learning -- Optimization for Deep Networks
Lénaïc Chizat · Edouard Oyallon · Francis Bach
[ Paper]  [ Poster] 
Poster
Tue Dec 10 05:30 PM -- 07:30 PM (PST) @ East Exhibition Hall B + C #96
Reducing the variance in online optimization by transporting past gradients
In Deep Learning -- Optimization for Deep Networks
Sébastien Arnold · Pierre-Antoine Manzagol · Reza Babanezhad Harikandeh · Ioannis Mitliagkas · Nicolas Le Roux
[ Paper]  [ Poster]  [ Slides] 
Poster
Tue Dec 10 05:30 PM -- 07:30 PM (PST) @ East Exhibition Hall B + C #97
Tight Sample Complexity of Learning One-hidden-layer Convolutional Neural Networks
In Deep Learning -- Optimization for Deep Networks
Yuan Cao · Quanquan Gu
[ Paper]  [ Poster] 
Poster
Tue Dec 10 05:30 PM -- 07:30 PM (PST) @ East Exhibition Hall B + C #98
Understanding and Improving Layer Normalization
In Deep Learning -- Optimization for Deep Networks
Jingjing Xu · Xu Sun · Zhiyuan Zhang · Guangxiang Zhao · Junyang Lin
[ Paper]  [ Poster] 
Poster
Tue Dec 10 05:30 PM -- 07:30 PM (PST) @ East Exhibition Hall B + C #99
LCA: Loss Change Allocation for Neural Network Training
In Deep Learning -- Optimization for Deep Networks
Janice Lan · Rosanne Liu · Hattie Zhou · Jason Yosinski
[ Paper]  [ Poster]