Skip to content
conftrace_

batch size

55 papers

Explore in graph

Co-occurring keywords · papers mentioning both

stochastic gradient descent (17) learning rate (13) large language model (4) gradient variance (4) convergence analysis (4) neural network (3) convergence rate (3) gradient descent (3) neural network optimization (3) neural network training (3)

Papers

Don't Decay the Learning Rate, Increase the Batch Size ICLR 2018 Efficient nonmyopic batch active search NeurIPS 2018 How SGD Selects the Global Minima in Over-parameterized Learning: A Dynamical Stability Perspective NeurIPS 2018 Adaptive Batch Size for Safe Policy Gradients NeurIPS 2017 Statistical Tests for Optimization Efficiency NeurIPS 2011