Co-occurring keywords · papers mentioning both
Papers
Catastrophic Fisher Explosion: Early Phase Fisher Matrix Impacts Generalization
ICML 2021
Extreme Memorization via Scale of Initialization
ICLR 2021
Frivolous Units: Wider Networks Are Not Really That Wide
AAAI 2021
Generalization Performance of Multi-pass Stochastic Gradient Descent with Convex Loss Functions
JMLR 2021
Implicit Gradient Regularization
ICLR 2021
Implicit Regularization in Matrix Sensing via Mirror Descent
NeurIPS 2021
Implicit Regularization in ReLU Networks with the Square Loss
COLT 2021
Implicit Regularization in Tensor Factorization
ICML 2021
Implicit Regularization via Neural Feature Alignment
AISTATS 2021
Implicit Self-Regularization in Deep Neural Networks: Evidence from Random Matrix Theory and Implications for Learning
JMLR 2021
Implicit Sparse Regularization: The Impact of Depth and Early Stopping
NeurIPS 2021
Label Noise SGD Provably Prefers Flat Global Minimizers
NeurIPS 2021
Noise against noise: stochastic label noise helps combat inherent label noise
ICLR 2021
Noisy Recurrent Neural Networks
NeurIPS 2021
On the Origin of Implicit Regularization in Stochastic Gradient Descent
ICLR 2021
Positive-Negative Momentum: Manipulating Stochastic Gradient Noise to Improve Generalization
ICML 2021
SGD: The Role of Implicit Regularization, Batch-size and Multiple-epochs
NeurIPS 2021
Shape Matters: Understanding the Implicit Bias of the Noise Covariance
COLT 2021
The Benefits of Implicit Regularization from SGD in Least Squares Problems
NeurIPS 2021
Towards Resolving the Implicit Bias of Gradient Descent for Matrix Factorization: Greedy Low-Rank Learning
ICLR 2021
Bad Global Minima Exist and SGD Can Reach Them
NeurIPS 2020
Can Implicit Bias Explain Generalization? Stochastic Convex Optimization as a Case Study
NeurIPS 2020
Decentralised Learning with Random Features and Distributed Gradient Descent
ICML 2020
Exact expressions for double descent and implicit regularization via surrogate random design
NeurIPS 2020
Gradient descent follows the regularization path for general losses
COLT 2020