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

Neural Network Optimization

3,648 papers

Papers per year

Papers

SAPE: Spatially-Adaptive Progressive Encoding for Neural Optimization NIPS 2021
What can linearized neural networks actually say about generalization? NIPS 2021
SUPER-ADAM: Faster and Universal Framework of Adaptive Gradients NIPS 2021
When Expressivity Meets Trainability: Fewer than $n$ Neurons Can Work NIPS 2021
Dynamics of Stochastic Momentum Methods on Large-scale, Quadratic Models NIPS 2021
Low-Fidelity Video Encoder Optimization for Temporal Action Localization NIPS 2021
A single gradient step finds adversarial examples on random two-layers neural networks NIPS 2021
Subquadratic Overparameterization for Shallow Neural Networks NIPS 2021
Hyperparameter Tuning is All You Need for LISTA NIPS 2021
On Plasticity, Invariance, and Mutually Frozen Weights in Sequential Task Learning NIPS 2021
On the Validity of Modeling SGD with Stochastic Differential Equations (SDEs) NIPS 2021
Sanity Checks for Lottery Tickets: Does Your Winning Ticket Really Win the Jackpot? NIPS 2021
Gradient Descent on Two-layer Nets: Margin Maximization and Simplicity Bias NIPS 2021
Channel Permutations for N:M Sparsity NIPS 2021
Nonsmooth Implicit Differentiation for Machine-Learning and Optimization NIPS 2021
Convergence of adaptive algorithms for constrained weakly convex optimization NIPS 2021
On the Convergence of Step Decay Step-Size for Stochastic Optimization NIPS 2021
Embedding Principle of Loss Landscape of Deep Neural Networks NIPS 2021
M-FAC: Efficient Matrix-Free Approximations of Second-Order Information NIPS 2021
Random Shuffling Beats SGD Only After Many Epochs on Ill-Conditioned Problems NIPS 2021
Analytic Study of Families of Spurious Minima in Two-Layer ReLU Neural Networks: A Tale of Symmetry II NIPS 2021
Efficient Neural Network Training via Forward and Backward Propagation Sparsification NIPS 2021
Augmented Shortcuts for Vision Transformers NIPS 2021
GradInit: Learning to Initialize Neural Networks for Stable and Efficient Training NIPS 2021
Differentiable Multiple Shooting Layers NIPS 2021