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

Neural Network Optimization

3,648 papers

Papers per year

Papers

Deep Learning on a Data Diet: Finding Important Examples Early in Training NIPS 2021
Symplectic Adjoint Method for Exact Gradient of Neural ODE with Minimal Memory NIPS 2021
MEST: Accurate and Fast Memory-Economic Sparse Training Framework on the Edge NIPS 2021
On the Periodic Behavior of Neural Network Training with Batch Normalization and Weight Decay NIPS 2021
Last iterate convergence of SGD for Least-Squares in the Interpolation regime. NIPS 2021
Understanding How Encoder-Decoder Architectures Attend NIPS 2021
Sparse Deep Learning: A New Framework Immune to Local Traps and Miscalibration NIPS 2021
SWAD: Domain Generalization by Seeking Flat Minima NIPS 2021
Fast Extra Gradient Methods for Smooth Structured Nonconvex-Nonconcave Minimax Problems NIPS 2021
Revisiting ResNets: Improved Training and Scaling Strategies NIPS 2021
Does Preprocessing Help Training Over-parameterized Neural Networks? NIPS 2021
Differentiable Spike: Rethinking Gradient-Descent for Training Spiking Neural Networks NIPS 2021
Small random initialization is akin to spectral learning: Optimization and generalization guarantees for overparameterized low-rank matrix reconstruction NIPS 2021
Analytic Insights into Structure and Rank of Neural Network Hessian Maps NIPS 2021
Training Neural Networks with Fixed Sparse Masks NIPS 2021
On Training Implicit Models NIPS 2021
Adaptive Proximal Gradient Methods for Structured Neural Networks NIPS 2021
Understanding and Improving Early Stopping for Learning with Noisy Labels NIPS 2021
Coupled Gradient Estimators for Discrete Latent Variables NIPS 2021
Second-Order Neural ODE Optimizer NIPS 2021
Learning Frequency Domain Approximation for Binary Neural Networks NIPS 2021
Characterizing possible failure modes in physics-informed neural networks NIPS 2021
The Elastic Lottery Ticket Hypothesis NIPS 2021
Improving Deep Learning Interpretability by Saliency Guided Training NIPS 2021
Representation Costs of Linear Neural Networks: Analysis and Design NIPS 2021