The Early Phase of Neural Network Training

24 February 2020

Papers citing "The Early Phase of Neural Network Training"

8 / 8 papers shown

Title
ALinFiK: Learning to Approximate Linearized Future Influence Kernel for Scalable Third-Party LLM Data Valuation Yanzhou Pan Huawei Lin Yide Ran Jiamin Chen Xiaodong Yu Weijie Zhao Denghui Zhang Zhaozhuo Xu 54 1 0 02 Mar 2025
The Silent Majority: Demystifying Memorization Effect in the Presence of Spurious Correlations Chenyu You Haocheng Dai Yifei Min Jasjeet Sekhon S. Joshi James S. Duncan 79 3 0 01 Jan 2025
Sharpness-Aware Minimization Efficiently Selects Flatter Minima Late in Training Zhanpeng Zhou Mingze Wang Yuchen Mao Bingrui Li Junchi Yan AAML 71 1 0 14 Oct 2024
Can Optimization Trajectories Explain Multi-Task Transfer? David Mueller Mark Dredze Nicholas Andrews 95 1 0 26 Aug 2024
Q-Newton: Hybrid Quantum-Classical Scheduling for Accelerating Neural Network Training with Newton's Gradient Descent Pingzhi Li Junyu Liu Hanrui Wang Tianlong Chen 116 1 0 30 Apr 2024
Drawing Robust Scratch Tickets: Subnetworks with Inborn Robustness Are Found within Randomly Initialized Networks Yonggan Fu Qixuan Yu Yang Zhang Shan-Hung Wu Ouyang Xu David D. Cox Yingyan Lin AAML OOD 54 29 0 26 Oct 2021
Time Matters in Regularizing Deep Networks: Weight Decay and Data Augmentation Affect Early Learning Dynamics, Matter Little Near Convergence Aditya Golatkar Alessandro Achille Stefano Soatto 49 95 0 30 May 2019
Learning both Weights and Connections for Efficient Neural Networks Song Han Jeff Pool J. Tran W. Dally CVBM 178 6,628 0 08 Jun 2015