Noise Consistency Training adds new controls to pre-trained one-step generators by training a lightweight adapter with a noise-space consistency loss, matching conditional generation quality at a fraction of the compute.
Constrained Learning with Non-Convex Losses
1 Pith paper cite this work. Polarity classification is still indexing.
abstract
Though learning has become a core component of modern information processing, there is now ample evidence that it can lead to biased, unsafe, and prejudiced systems. The need to impose requirements on learning is therefore paramount, especially as it reaches critical applications in social, industrial, and medical domains. However, the non-convexity of most modern statistical problems is only exacerbated by the introduction of constraints. Whereas good unconstrained solutions can often be learned using empirical risk minimization, even obtaining a model that satisfies statistical constraints can be challenging. All the more so, a good one. In this paper, we overcome this issue by learning in the empirical dual domain, where constrained statistical learning problems become unconstrained and deterministic. We analyze the generalization properties of this approach by bounding the empirical duality gap -- i.e., the difference between our approximate, tractable solution and the solution of the original (non-convex) statistical problem -- and provide a practical constrained learning algorithm. These results establish a constrained counterpart to classical learning theory, enabling the explicit use of constraints in learning. We illustrate this theory and algorithm in rate-constrained learning applications arising in fairness and adversarial robustness.
citation-role summary
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Noise Consistency Training: A Native Approach for One-Step Generator in Learning Additional Controls
Noise Consistency Training adds new controls to pre-trained one-step generators by training a lightweight adapter with a noise-space consistency loss, matching conditional generation quality at a fraction of the compute.