Skip to yearly menu bar Skip to main content


(8 events)   Timezone:  
Show all
The 2021 schedule is still incomplete
Toggle Poster Visibility
Oral
Wed Jul 21 06:00 PM -- 06:20 PM (PDT)
RATT: Leveraging Unlabeled Data to Guarantee Generalization
In Learning Theory 10
Saurabh Garg · Sivaraman Balakrishnan · Zico Kolter · Zachary Lipton
[ Paper ]
Spotlight
Wed Jul 21 06:20 PM -- 06:25 PM (PDT)
Approximation Theory of Convolutional Architectures for Time Series Modelling
In Learning Theory 10
Haotian Jiang · Zhong Li · Qianxiao Li
[ Paper ]
Spotlight
Wed Jul 21 06:25 PM -- 06:30 PM (PDT)
On the Generalization Power of Overfitted Two-Layer Neural Tangent Kernel Models
In Learning Theory 10
Peizhong Ju · Xiaojun Lin · Ness Shroff
[ Paper ]
Spotlight
Wed Jul 21 06:30 PM -- 06:35 PM (PDT)
Geometry of the Loss Landscape in Overparameterized Neural Networks: Symmetries and Invariances
In Learning Theory 10
Berfin Simsek · François Ged · Arthur Jacot · Francesco Spadaro · Clement Hongler · Wulfram Gerstner · Johanni Brea
[ Paper ]
Spotlight
Wed Jul 21 06:35 PM -- 06:40 PM (PDT)
On the Explicit Role of Initialization on the Convergence and Implicit Bias of Overparametrized Linear Networks
In Learning Theory 10
Hancheng Min · Salma Tarmoun · Rene Vidal · Enrique Mallada
[ Paper ]
Spotlight
Wed Jul 21 06:40 PM -- 06:45 PM (PDT)
Relative Deviation Margin Bounds
In Learning Theory 10
Corinna Cortes · Mehryar Mohri · Ananda Theertha Suresh
[ Paper ]
Spotlight
Wed Jul 21 06:45 PM -- 06:50 PM (PDT)
Accuracy on the Line: on the Strong Correlation Between Out-of-Distribution and In-Distribution Generalization
In Learning Theory 10
John Miller · Rohan Taori · Aditi Raghunathan · Shiori Sagawa · Pang Wei Koh · Vaishaal Shankar · Percy Liang · Yair Carmon · Ludwig Schmidt
[ Paper ]
Q&A
Wed Jul 21 06:50 PM -- 06:55 PM (PDT)
Q&A
In Learning Theory 10