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

Neural Network Optimization

3,649 papers

Papers per year

2
5
40
414
386
'05
'10
'15
'20
'25

Papers

Gradient Descent: The Ultimate Optimizer NIPS 2022
GraB: Finding Provably Better Data Permutations than Random Reshuffling NIPS 2022
Amortized Proximal Optimization NIPS 2022
Fast Mixing of Stochastic Gradient Descent with Normalization and Weight Decay NIPS 2022
Sparse Structure Search for Delta Tuning NIPS 2022
Robustness to Unbounded Smoothness of Generalized SignSGD NIPS 2022
Analyzing Sharpness along GD Trajectory: Progressive Sharpening and Edge of Stability NIPS 2022
Generalization Bounds for Gradient Methods via Discrete and Continuous Prior NIPS 2022
Convergence beyond the over-parameterized regime using Rayleigh quotients NIPS 2022
Stochastic Second-Order Methods Improve Best-Known Sample Complexity of SGD for Gradient-Dominated Functions NIPS 2022
Learning Distributions Generated by Single-Layer ReLU Networks in the Presence of Arbitrary Outliers NIPS 2022
Momentum Aggregation for Private Non-convex ERM NIPS 2022
Nest Your Adaptive Algorithm for Parameter-Agnostic Nonconvex Minimax Optimization NIPS 2022
Introspective Learning : A Two-Stage approach for Inference in Neural Networks NIPS 2022
In Defense of the Unitary Scalarization for Deep Multi-Task Learning NIPS 2022
Making Look-Ahead Active Learning Strategies Feasible with Neural Tangent Kernels NIPS 2022
Holomorphic Equilibrium Propagation Computes Exact Gradients Through Finite Size Oscillations NIPS 2022
Do Current Multi-Task Optimization Methods in Deep Learning Even Help? NIPS 2022
Stochastic Adaptive Activation Function NIPS 2022
Training Scale-Invariant Neural Networks on the Sphere Can Happen in Three Regimes NIPS 2022
projUNN: efficient method for training deep networks with unitary matrices NIPS 2022
Rare Gems: Finding Lottery Tickets at Initialization NIPS 2022
Identifying good directions to escape the NTK regime and efficiently learn low-degree plus sparse polynomials NIPS 2022
On global convergence of ResNets: From finite to infinite width using linear parameterization NIPS 2022
Provable Generalization of Overparameterized Meta-learning Trained with SGD NIPS 2022