Toggle Poster Visibility
Spotlight
Wed Jul 20 07:30 AM -- 07:35 AM (PDT) @ Room 309
On Numerical Integration in Neural Ordinary Differential Equations
In
DL: Theory
Spotlight
Wed Jul 20 07:35 AM -- 07:40 AM (PDT) @ Room 309
Reverse Engineering the Neural Tangent Kernel
In
DL: Theory
Spotlight
Wed Jul 20 07:40 AM -- 07:45 AM (PDT) @ Room 309
Principled Knowledge Extrapolation with GANs
In
DL: Theory
Spotlight
Wed Jul 20 07:45 AM -- 07:50 AM (PDT) @ Room 309
Informed Learning by Wide Neural Networks: Convergence, Generalization and Sampling Complexity
In
DL: Theory
Spotlight
Wed Jul 20 07:50 AM -- 07:55 AM (PDT) @ Room 309
Data Augmentation as Feature Manipulation
In
DL: Theory
Spotlight
Wed Jul 20 07:55 AM -- 08:00 AM (PDT) @ Room 309
Convolutional and Residual Networks Provably Contain Lottery Tickets
In
DL: Theory
Spotlight
Wed Jul 20 08:00 AM -- 08:05 AM (PDT) @ Room 309
Feature Learning and Signal Propagation in Deep Neural Networks
In
DL: Theory
Oral
Wed Jul 20 08:05 AM -- 08:25 AM (PDT) @ Room 309
Robust Training of Neural Networks Using Scale Invariant Architectures
In
DL: Theory
Spotlight
Wed Jul 20 08:25 AM -- 08:30 AM (PDT) @ Room 309
Understanding Contrastive Learning Requires Incorporating Inductive Biases
In
DL: Theory
Spotlight
Wed Jul 20 08:30 AM -- 08:35 AM (PDT) @ Room 309
Implicit Regularization with Polynomial Growth in Deep Tensor Factorization
In
DL: Theory
Spotlight
Wed Jul 20 08:35 AM -- 08:40 AM (PDT) @ Room 309
Deep Network Approximation in Terms of Intrinsic Parameters
In
DL: Theory
Spotlight
Wed Jul 20 08:40 AM -- 08:45 AM (PDT) @ Room 309
Coin Flipping Neural Networks
In
DL: Theory
Spotlight
Wed Jul 20 08:45 AM -- 08:50 AM (PDT) @ Room 309
Benefits of Overparameterized Convolutional Residual Networks: Function Approximation under Smoothness Constraint
In
DL: Theory
Spotlight
Wed Jul 20 08:50 AM -- 08:55 AM (PDT) @ Room 309
More Than a Toy: Random Matrix Models Predict How Real-World Neural Representations Generalize
In
DL: Theory
Spotlight
Wed Jul 20 08:55 AM -- 09:00 AM (PDT) @ Room 309
SE(3) Equivariant Graph Neural Networks with Complete Local Frames
In
DL: Theory
[
Paper PDF]