Toggle Poster Visibility
Spotlight
Wed Jul 20 11:30 PM -- 11:35 PM (KST) @ Room 309
On Numerical Integration in Neural Ordinary Differential Equations
In
DL: Theory
Spotlight
Wed Jul 20 11:35 PM -- 11:40 PM (KST) @ Room 309
Reverse Engineering the Neural Tangent Kernel
In
DL: Theory
Spotlight
Wed Jul 20 11:40 PM -- 11:45 PM (KST) @ Room 309
Principled Knowledge Extrapolation with GANs
In
DL: Theory
Spotlight
Wed Jul 20 11:45 PM -- 11:50 PM (KST) @ Room 309
Informed Learning by Wide Neural Networks: Convergence, Generalization and Sampling Complexity
In
DL: Theory
Spotlight
Wed Jul 20 11:50 PM -- 11:55 PM (KST) @ Room 309
Data Augmentation as Feature Manipulation
In
DL: Theory
Spotlight
Wed Jul 20 11:55 PM -- 12:00 AM (KST) @ Room 309
Convolutional and Residual Networks Provably Contain Lottery Tickets
In
DL: Theory
Spotlight
Thu Jul 21 12:00 AM -- 12:05 AM (KST) @ Room 309
Feature Learning and Signal Propagation in Deep Neural Networks
In
DL: Theory
Oral
Thu Jul 21 12:05 AM -- 12:25 AM (KST) @ Room 309
Robust Training of Neural Networks Using Scale Invariant Architectures
In
DL: Theory
Spotlight
Thu Jul 21 12:25 AM -- 12:30 AM (KST) @ Room 309
Understanding Contrastive Learning Requires Incorporating Inductive Biases
In
DL: Theory
Spotlight
Thu Jul 21 12:30 AM -- 12:35 AM (KST) @ Room 309
Implicit Regularization with Polynomial Growth in Deep Tensor Factorization
In
DL: Theory
Spotlight
Thu Jul 21 12:35 AM -- 12:40 AM (KST) @ Room 309
Deep Network Approximation in Terms of Intrinsic Parameters
In
DL: Theory
Spotlight
Thu Jul 21 12:40 AM -- 12:45 AM (KST) @ Room 309
Coin Flipping Neural Networks
In
DL: Theory
Spotlight
Thu Jul 21 12:45 AM -- 12:50 AM (KST) @ Room 309
Benefits of Overparameterized Convolutional Residual Networks: Function Approximation under Smoothness Constraint
In
DL: Theory
Spotlight
Thu Jul 21 12:50 AM -- 12:55 AM (KST) @ Room 309
More Than a Toy: Random Matrix Models Predict How Real-World Neural Representations Generalize
In
DL: Theory
Spotlight
Thu Jul 21 12:55 AM -- 01:00 AM (KST) @ Room 309
SE(3) Equivariant Graph Neural Networks with Complete Local Frames
In
DL: Theory
[
Paper PDF]
Successful Page Load