4 papers
Fast and Furious Symmetric Learning in Zero-Sum Games: Gradient Descent as Fictitious Play
John Lazarsfeld, Georgios Piliouras, Ryann Sim +1
This paper investigates the sublinear regret guarantees of two non-no-regret algorithms in zero-sum games: Fictitious Play, and Online Gradient Descent with constant stepsizes. In…
Hamiltonian Descent Algorithms for Optimization: Accelerated Rates via Randomized Integration Time
Qiang Fu, Andre Wibisono
We study the Hamiltonian flow for optimization (HF-opt), which simulates the Hamiltonian dynamics for some integration time and resets the velocity to to decrease the objective…
Mixing Time of the Proximal Sampler in Relative Fisher Information via Strong Data Processing Inequality
Andre Wibisono
We study the mixing time guarantee for sampling in relative Fisher information via the Proximal Sampler algorithm, which is an approximate proximal discretization of the Langevin d…
High-accuracy sampling from constrained spaces with the Metropolis-adjusted Preconditioned Langevin Algorithm
Vishwak Srinivasan, Andre Wibisono, Ashia Wilson
In this work, we propose a first-order sampling method called the Metropolis-adjusted Preconditioned Langevin Algorithm for approximate sampling from a target distribution whose su…