arXiv:2609.06467v1 Announce Type: new
Abstract: In performative reinforcement learning the deployed policy shapes the environment that generates the learner's future data, and the natural solution co...
By Debmalya Mandal
arXiv:2608.25279v1 Announce Type: cross
Abstract: The OBABO and BAOAB schemes and the other standard Strang splittings of kinetic (underdamped) Langevin dynamics are widely used Markov chain Monte Ca...
By Nawaf Bou-Rabee
arXiv:2610.02158v1 Announce Type: cross
Abstract: We consider the problem of sampling from Gibbs distributions on matrix spaces whose potential energies are neither convex nor globally gradient-Lipsc...
By Nikolaos Makras, Sotirios Sabanis
arXiv:2608. 06283v1 Announce Type: new Abstract: We study the problem of sampling from target distributions whose potentials are simultaneously non-smooth, subject to superlinear gradient growth, and non-convex.
By Iosif Lytras, Nikolaos Makras, Sotirios Sabanis
We study the problem of sampling from target distributions whose potentials are simultaneously non-smooth, subject to superlinear gradient growth, and non-convex. We introduce the Subgradient Tamed Unadjusted Langevin Algorithm (SG-TULA), a discretisation of the Langevin diffusion that operates directly on subgradients, without relying on computationally demanding smoothing procedures.
arXiv:2607. 11752v1 Announce Type: cross Abstract: For decades, static solution concepts (Nash, Correlated, and Coarse Correlated Equilibria) and the Price of Anarchy (PoA) have formed the bedrock of algorithmic game theory, with no-regret learning proving fast convergence to such game-theoretic equilibria.
By Georgios Piliouras, Ian Gemp, Siqi Liu, Luke Marris