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

Neural Network Optimization

3,648 papers

Papers per year

Papers

Intractability of Learning the Discrete Logarithm with Gradient-Based Methods ACML 2023
Can Infinitely Wide Deep Nets Help Small-data Multi-label Learning? ACML 2023
Revisiting Structured Dropout ACML 2023
Global Convergence of Over-parameterized Deep Equilibrium Models AISTATS 2023
On the Neural Tangent Kernel Analysis of Randomly Pruned Neural Networks AISTATS 2023
Exact Gradient Computation for Spiking Neural Networks via Forward Propagation AISTATS 2023
Linear Convergence of Gradient Descent For Finite Width Over-parametrized Linear Networks With General Initialization AISTATS 2023
Mind the (optimality) Gap: A Gap-Aware Learning Rate Scheduler for Adversarial Nets AISTATS 2023
Learning Physics-Informed Neural Networks without Stacked Back-propagation AISTATS 2023
ASkewSGD : An Annealed interval-constrained Optimisation method to train Quantized Neural Networks AISTATS 2023
Conjugate Gradient Method for Generative Adversarial Networks AISTATS 2023
Nyström Method for Accurate and Scalable Implicit Differentiation AISTATS 2023
Neural Discovery of Permutation Subgroups AISTATS 2023
LOFT: Finding Lottery Tickets through Filter-wise Training AISTATS 2023
Strong Lottery Ticket Hypothesis with $\varepsilon$–perturbation AISTATS 2023
On the Accelerated Noise-Tolerant Power Method AISTATS 2023
Meta-Learning with Adjoint Methods AISTATS 2023
Explicit Regularization in Overparametrized Models via Noise Injection AISTATS 2023
A Mini-Block Fisher Method for Deep Neural Networks AISTATS 2023
Learning to Generalize Provably in Learning to Optimize AISTATS 2023
On the Implicit Geometry of Cross-Entropy Parameterizations for Label-Imbalanced Data AISTATS 2023
Robust Linear Regression: Gradient-descent, Early-stopping, and Beyond AISTATS 2023
Beyond Uniform Smoothness: A Stopped Analysis of Adaptive SGD COLT 2023
Convergence of AdaGrad for Non-convex Objectives: Simple Proofs and Relaxed Assumptions COLT 2023
Over-Parameterization Exponentially Slows Down Gradient Descent for Learning a Single Neuron COLT 2023