Quantized Stochastic Primal-Dual Methods for Distributed Optimization under Relaxed Global Geometry

Susmit Sarkar, Abhinav Raghuvanshi, Kushal Chakrabarti, Mayank Baranwal

Thursday at 04:00

5 Views

0 Comments

arXiv:2606.11339v1 Announce Type: cross Abstract: We study distributed optimization with stochastic gradients and finite-bit communication modeled by random (unbiased) quantization. We propose q-PDGD, a quantized stochastic primal-dual method, and analyze it under relaxed global geometry. Under restricted secant inequality (RSI), a constant...

Read the full article at the source.

Read Original Article

Was this helpful?