9 papers
Everywhere Learning: Artificial Intelligence with Pointwise Constraints
Ignacio Boero, Ignacio Hounie, Luiz Chamon +1
Everywhere learning is a new paradigm whereby Artificial Intelligence (AI) systems are trained to satisfy loss constraints with probability one over the data distribution. This is…
Adaptive Symmetrization of the KL Divergence
Omri Ben-Dov, Luiz F. O. Chamon
The forward Kullback-Leibler (KL) divergence is a ubiquitous objective for fitting a parameterized distribution to samples due to its tractability and equivalence to maximum likeli…
Learning with Statistical Equality Constraints
Aneesh Barthakur, Luiz F. O. Chamon
As machine learning applications grow increasingly ubiquitous and complex, they face an increasing set of requirements beyond accuracy. The prevalent approach to handle this challe…
Sampling with Shielded Langevin Monte Carlo Using Navigation Potentials
Nicolas Zilberstein, Santiago Segarra, Luiz Chamon
We introduce shielded Langevin Monte Carlo (LMC), a constrained sampler inspired by navigation functions, capable of sampling from unnormalized target distributions defined over pu…
Learning (Approximately) Equivariant Networks via Constrained Optimization
Andrei Manolache, Luiz F. O. Chamon, Mathias Niepert
Equivariant neural networks are designed to respect symmetries through their architecture, boosting generalization and sample efficiency when those symmetries are present in the da…
The Lagrangian Method for Solving Constrained Markov Games
Soham Das, Santiago Paternain, Luiz F. O. Chamon +1
We propose the concept of a Lagrangian game to solve constrained Markov games. Such games model scenarios where agents face cost constraints in addition to their individual rewards…