The development of efficient sampling algorithms catering to non-Euclide...
SGD (with momentum) and AdamW are the two most used optimizers for
fine-...
We study the convergence rate of discretized Riemannian Hamiltonian Mont...
We propose a new framework for differentially private optimization of co...
Data augmentation is a cornerstone of the machine learning pipeline, yet...
Early stopping is a simple and widely used method to prevent over-traini...
We demonstrate for the first time that ill-conditioned, non-smooth,
cons...
Classically, the continuous-time Langevin diffusion converges exponentia...
We give lower bounds on the performance of two of the most popular sampl...
We study exploration using randomized value functions in Thompson Sampli...
We give algorithms for sampling several structured logconcave families t...
Leverage score sampling is a powerful technique that originates from
the...
We consider sampling from composite densities on ℝ^d of the form
dπ(x) ∝...
Particle filtering is a popular method for inferring latent states in
st...
We show that the gradient norm ∇ f(x) for x ∼(-f(x)),
where f is strongl...
Sampling from log-concave distributions is a well researched problem tha...