Samuel L Smith
6 papers · 2021–2024 · 2 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🗺️
Taxonomy Completionist
(13)
🏆
Keyword Champion
(2)
Top co-authors
Research topics
Deep Learning
(6)
Machine Learning
(5)
Architectures
(4)
Optimization & Theory · Machine Learning
(3)
Techniques
(3)
Artificial Intelligence
(1)
Application Areas
(1)
Core AI
(1)
Core Methods
(1)
Learning Types · Machine Learning
(1)
Learning Types · Deep Learning
(1)
Models
(1)
Optimization & Theory · Deep Learning
(1)
Keywords
residual network
(2)
batch normalization
(2)
signal propagation
(2)
neural network optimization
(1)
image recognition
(1)
learning rate
(1)
state space model
(1)
recurrent neural network
(1)
gradient flow
(1)
implicit regularization
(1)
long sequence modeling
(1)
parameter initialization
(1)
layer normalization
(1)
vanishing gradient
(1)
parallel training
(1)
linear recurrent unit
(1)
mini-batch gradient
(1)
long-range arena
(1)
weight standardization
(1)
nonlinear projection
(1)
Papers
Universality of Linear Recurrences Followed by Non-linear Projections: Finite-Width Guarantees and Benefits of Complex Eigenvalues
ICML 2024
Deep Transformers without Shortcuts: Modifying Self-attention for Faithful Signal Propagation
ICLR 2023
Resurrecting Recurrent Neural Networks for Long Sequences
ICML 2023
Characterizing signal propagation to close the performance gap in unnormalized ResNets
ICLR 2021
High-Performance Large-Scale Image Recognition Without Normalization
ICML 2021
On the Origin of Implicit Regularization in Stochastic Gradient Descent
ICLR 2021