conftrace_

implicit regularization

93 papers

Explore in graph

Co-occurring keywords

gradient descent (1144) stochastic gradient descent (1091) neural network (6616) neural network optimization (1293) deep neural network (1803) gradient flow (142) ridge regression (134) matrix factorization (529) matrix sensing (24) stochastic differential equation (181)

Papers

The Benefits of Implicit Regularization from SGD in Least Squares Problems NIPS 2021
SGD: The Role of Implicit Regularization, Batch-size and Multiple-epochs NIPS 2021
Implicit Self-Regularization in Deep Neural Networks: Evidence from Random Matrix Theory and Implications for Learning JMLR 2021
Catastrophic Fisher Explosion: Early Phase Fisher Matrix Impacts Generalization ICML 2021
Label Noise SGD Provably Prefers Flat Global Minimizers NIPS 2021
Implicit Sparse Regularization: The Impact of Depth and Early Stopping NIPS 2021
Shape Matters: Understanding the Implicit Bias of the Noise Covariance COLT 2021
Generalization Performance of Multi-pass Stochastic Gradient Descent with Convex Loss Functions JMLR 2021
Noisy Recurrent Neural Networks NIPS 2021
Implicit Regularization in ReLU Networks with the Square Loss COLT 2021
Implicit Regularization in Matrix Sensing via Mirror Descent NIPS 2021
Frivolous Units: Wider Networks Are Not Really That Wide AAAI 2021
Implicit Regularization in Tensor Factorization ICML 2021
Positive-Negative Momentum: Manipulating Stochastic Gradient Noise to Improve Generalization ICML 2021
The Implicit Regularization of Stochastic Gradient Flow for Least Squares ICML 2020
Bad Global Minima Exist and SGD Can Reach Them NIPS 2020
Gradient descent follows the regularization path for general losses COLT 2020
Implicit regularization for deep neural networks driven by an Ornstein-Uhlenbeck like process COLT 2020
The Statistical Complexity of Early-Stopped Mirror Descent NIPS 2020
Decentralised Learning with Random Features and Distributed Gradient Descent ICML 2020
Implicit Regularization and Convergence for Weight Normalization NIPS 2020
On Implicit Regularization in $β$-VAEs ICML 2020
The Optimal Ridge Penalty for Real-world High-dimensional Data Can Be Zero or Negative due to the Implicit Ridge Regularization JMLR 2020
Exact expressions for double descent and implicit regularization via surrogate random design NIPS 2020
Can Implicit Bias Explain Generalization? Stochastic Convex Optimization as a Case Study NIPS 2020