The authors study a penalized Wasserstein DRO formulation where an adversary may choose any distribution but incurs a penalty for deviating from the empirical distribution.
Cyclical monotonicity enforces efficient adversarial transport in robust learning
Authors show that optimal adversarial transport maps must be cyclically monotone, and propose two methods to enforce this property, outperforming standard adversarial training.
Big Tech
EPFL · Apple
Research Digest··3 min read
The authors reformulate distributionally robust optimization (DRO) as a problem over transport maps and prove that optimal maps are cyclically monotone.
Why this paper
From Apple and EPFL
In one line
Adversarial training violates optimal transport geometry; enforcing cyclical monotonicity via MPA or ICNN improves robustness.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ✓Limitations stated by the authors
- ·No benchmark numbers found
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§