conftrace_

optimization theory

45 papers

Explore in graph

Co-occurring keywords

stochastic gradient descent (1091) gradient descent (1144) convergence analysis (395) convergence rate (607) convex optimization (1321) neural network optimization (1293) implicit bia (107) neural network (6616) non-convex optimization (547) generalization bound (652)

Papers

Error Analysis Affected by Heavy-Tailed Gradients for Non-Convex Pairwise Stochastic Gradient Descent AAAI 2025
From Activation to Initialization: Scaling Insights for Optimizing Neural Fields CVPR 2024
Towards Stability and Generalization Bounds in Decentralized Minibatch Stochastic Gradient Descent AAAI 2024
Provable Accelerated Convergence of Nesterov’s Momentum for Deep ReLU Neural Networks ALT 2024
On the Generalization of Stochastic Gradient Descent with Momentum JMLR 2024
Global Convergence in Training Large-Scale Transformers NIPS 2024
Faster Rates of Differentially Private Stochastic Convex Optimization JMLR 2024
Gradient Guidance for Diffusion Models: An Optimization Perspective NIPS 2024
Only Strict Saddles in the Energy Landscape of Predictive Coding Networks? NIPS 2024
Unraveling the Gradient Descent Dynamics of Transformers NIPS 2024
Error Analysis of Spherically Constrained Least Squares Reformulation in Solving the Stackelberg Prediction Game NIPS 2024
The Price of Adaptivity in Stochastic Convex Optimization COLT 2024
Implicit Bias of Gradient Descent for Two-layer ReLU and Leaky ReLU Networks on Nearly-orthogonal Data NIPS 2023
Momentum Ensures Convergence of SIGNSGD under Weaker Assumptions ICML 2023
TD Convergence: An Optimization Perspective NIPS 2023
Does a sparse ReLU network training problem always admit an optimum ? NIPS 2023
Large deviations rates for stochastic gradient descent with strongly convex functions AISTATS 2023
Power-Law Escape Rate of SGD ICML 2022
Oracle Complexity in Nonsmooth Nonconvex Optimization JMLR 2022
On Margin Maximization in Linear and ReLU Networks NIPS 2022
On Numerical Integration in Neural Ordinary Differential Equations ICML 2022
Embedding Principle of Loss Landscape of Deep Neural Networks NIPS 2021
Exponentially Many Local Minima in Quantum Neural Networks ICML 2021
Towards Understanding Why Lookahead Generalizes Better Than SGD and Beyond NIPS 2021
Hessian Eigenspectra of More Realistic Nonlinear Models NIPS 2021