Frequency-aware SGD for Efficient Embedding Learning with Provable
Benefits

v1v2v3 (latest)

Frequency-aware SGD for Efficient Embedding Learning with Provable Benefits

10 October 2021

Dhruv Choudhary

Bhargav Bhushanam

ArXiv (abs)PDF HTML

Papers citing "Frequency-aware SGD for Efficient Embedding Learning with Provable Benefits"

4 / 4 papers shown

Title
The Evolution of Embedding Table Optimization and Multi-Epoch Training in Pinterest Ads Conversion Andrew Qiu Shubham Barhate Hin Wai Lui Runze Su Rafael Rios Müller Kungang Li Ling Leng Han Sun Shayan Ehsani Zhifang Liu 94 0 0 08 May 2025
Large Batch Analysis for Adagrad Under Anisotropic Smoothness Yuxing Liu Boyao Wang Tong Zhang 62 6 0 21 Jun 2024
Heavy-Tailed Class Imbalance and Why Adam Outperforms Gradient Descent on Language Models Frederik Kunstner Robin Yadav Alan Milligan Mark Schmidt Alberto Bietti 95 34 0 29 Feb 2024
Outliers Dimensions that Disrupt Transformers Are Driven by Frequency Giovanni Puccetti Anna Rogers Aleksandr Drozd F. Dell’Orletta 174 45 0 23 May 2022