Statistical Learning
Stable Nonconvex-Nonconcave Training via Linear Interpolation
By replacing the inner optimizer in RAPP we rediscover the family of Lookahead algorithms for which we establish convergence in cohypomonotone problems even when the base optimizer is taken to be gradient descent ascent.
Provably Fast Finite Particle Variants of SVGD via Virtual Particle Stochastic Approximation
Although the population (i.e, infinite-particle) limit dynamics of SVGD is well characterized, its behavior in the finite-particle regime is far less understood.
Provably Fast Finite Particle Variants of SVGD via Virtual Particle Stochastic Approximation
Although the population (i.e, infinite-particle) limit dynamics of SVGD is well characterized, its behavior in the finite-particle regime is far less understood.
Sample-Efficient Constrained Reinforcement Learning with General Parameterization
Many articles in the literature solve the CMDP with an unknown environment.
Optimal Classification under Performative Distribution Shift
This approach can also be integrated into various change-of-variable-based models, such as V AEs or normalizing flows.