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

Neural Network Optimization

3,648 papers

Papers per year

Papers

BiSLS/SPS: Auto-tune Step Sizes for Stable Bi-level Optimization NIPS 2023
Minimum norm interpolation by perceptra: Explicit regularization and implicit bias NIPS 2023
Linear Convergence of Gradient Descent For Finite Width Over-parametrized Linear Networks With General Initialization AISTATS 2023
Modeling Stroke Mask for End-to-End Text Erasing WACV 2023
A Guide Through the Zoo of Biased SGD NIPS 2023
Are Straight-Through Gradients and Soft-Thresholding All You Need for Sparse Training? WACV 2023
Practical Sharpness-Aware Minimization Cannot Converge All the Way to Optima NIPS 2023
Strong Lottery Ticket Hypothesis with $\varepsilon$–perturbation AISTATS 2023
Low-Variance Gradient Estimation in Unrolled Computation Graphs with ES-Single ICML 2023
FIANCEE: Faster Inference of Adversarial Networks via Conditional Early Exits CVPR 2023
Kronecker-Factored Approximate Curvature for Modern Neural Network Architectures NIPS 2023
A Spectral Viewpoint on Continual Relation Extraction EMNLP 2023
SOL: Sampling-based Optimal Linear bounding of arbitrary scalar functions NIPS 2023
The Power of Preconditioning in Overparameterized Low-Rank Matrix Sensing ICML 2023
Train Faster, Perform Better: Modular Adaptive Training in Over-Parameterized Models NIPS 2023
Searching Efficient Neural Architecture With Multi-Resolution Fusion Transformer for Appearance-Based Gaze Estimation WACV 2023
The Geometry of Neural Nets' Parameter Spaces Under Reparametrization NIPS 2023
Gradient Descent Monotonically Decreases the Sharpness of Gradient Flow Solutions in Scalar Networks and Beyond ICML 2023
Dynamic Neural Network for Multi-Task Learning Searching Across Diverse Network Topologies CVPR 2023
HOTNAS: Hierarchical Optimal Transport for Neural Architecture Search CVPR 2023
Generalized Polyak Step Size for First Order Optimization with Momentum ICML 2023
Neural networks trained with SGD learn distributions of increasing complexity ICML 2023
Lon-eå at SemEval-2023 Task 11: A Comparison of Activation Functions for Soft and Hard Label Prediction SEMEVAL 2023
Challenging the “One Single Vector per Token” Assumption CONLL 2023
Mitigating Over-smoothing in Transformers via Regularized Nonlocal Functionals NIPS 2023