conftrace_
← Optimization & Theory
Machine Learning › Optimization & Theory ›

Neural Network Optimization

3,648 papers

Papers per year

Papers

UOR at SemEval-2021 Task 12: On Crowd Annotations; Learning with Disagreements to optimise crowd truth ACL 2021
CLUZH at SIGMORPHON 2021 Shared Task on Multilingual Grapheme-to-Phoneme Conversion: Variations on a Baseline ACL 2021
SmBoP: Semi-autoregressive Bottom-up Semantic Parsing ACL 2021
Understanding How Over-Parametrization Leads to Acceleration: A case of learning a single teacher neuron ACML 2021
The Power of Factorial Powers: New Parameter settings for (Stochastic) Optimization ACML 2021
An Optimistic Acceleration of AMSGrad for Nonconvex Optimization ACML 2021
calibrated adversarial training ACML 2021
Revisiting Weight Initialization of Deep Neural Networks ACML 2021
A Fast and Robust Method for Global Topological Functional Optimization AISTATS 2021
Learning to Defend by Learning to Attack AISTATS 2021
Regularization Matters: A Nonparametric Perspective on Overparametrized Neural Network AISTATS 2021
A Theoretical Analysis of Catastrophic Forgetting through the NTK Overlap Matrix AISTATS 2021
Learning with Hyperspherical Uniformity AISTATS 2021
A Study of Condition Numbers for First-Order Optimization AISTATS 2021
Stochastic Polyak Step-size for SGD: An Adaptive Learning Rate for Fast Convergence AISTATS 2021
SGD for Structured Nonconvex Functions: Learning Rates, Minibatching and Interpolation AISTATS 2021
Stable ResNet AISTATS 2021
Understanding Gradient Clipping In Incremental Gradient Methods AISTATS 2021
Noisy Gradient Descent Converges to Flat Minima for Nonconvex Matrix Factorization AISTATS 2021
Learning with Gradient Descent and Weakly Convex Losses AISTATS 2021
On the Suboptimality of Negative Momentum for Minimax Optimization AISTATS 2021
Fractional moment-preserving initialization schemes for training deep neural networks AISTATS 2021
Ridge Regression with Over-parametrized Two-Layer Networks Converge to Ridgelet Spectrum AISTATS 2021
Meta Learning in the Continuous Time Limit AISTATS 2021
A Dynamical View on Optimization Algorithms of Overparameterized Neural Networks AISTATS 2021