pith. sign in

9 should be interpreted as a coarsened upper bound obtained by regrouping lower-order contributions and absorbing universal constants into the dominant terms

presents a cleaner asymptotic form that emphasizes the dominant scaling behavior with respect to the number of rounds R, participation level S, local update stepsE, heterogeneityκ 2, stochastic gradient varianceζ 2 g as follows: O Lθ0 − · 2022

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
browse 1 citing papers

fields

cs.LG 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

Distributed Direct Preference Optimization

cs.LG · 2026-05-20 · unverdicted · novelty 7.0

First convergence analysis of DPO under federated and decentralized training, characterizing rates via client drift, communication frequency, preference heterogeneity, and graph spectral connectivity.

citing papers explorer

Showing 1 of 1 citing paper.

  • Distributed Direct Preference Optimization cs.LG · 2026-05-20 · unverdicted · none · ref 18

    First convergence analysis of DPO under federated and decentralized training, characterizing rates via client drift, communication frequency, preference heterogeneity, and graph spectral connectivity.