conftrace_

gradient error

5 papers

Explore in graph

Co-occurring keywords

loss trajectory (1) saddle point (95) mathematical problem-solving (6) gradient clustering (8) asynchronous parallel learning (1) dense feature model (1) large language model (13587) training trajectory (6) dense feature (5) test accuracy (6)

Papers

SmallToLarge (S2L): Scalable Data Selection for Fine-tuning Large Language Models by Summarizing Training Trajectories of Small Models NIPS 2024
Surrogate Module Learning: Reduce the Gradient Error Accumulation in Training Spiking Neural Networks ICML 2023
Online Saddle Point Tracking with Decision-Dependent Data L4DC 2023
Seizing Critical Learning Periods in Federated Learning AAAI 2022
Asynchronous Parallel Learning for Neural Networks and Structured Models with Dense Features COLING 2016