The work defines a family of surrogate losses for generative models and LLMs whose on-policy gradients match those of any f-divergence while sharing the same off-policy minimizer as the original MSE loss.
•Gradient Weight: wDG i = 1 α−1 e(α−1)∆i EB[e(α−1)∆(y)] −1 E
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
$f$-Trajectory Balance: A Loss Family for Tuning GFlowNets, Generative Models, and LLMs with Off- and On-Policy Data
The work defines a family of surrogate losses for generative models and LLMs whose on-policy gradients match those of any f-divergence while sharing the same off-policy minimizer as the original MSE loss.