Search Results for author:
Found 6 papers, 0 papers with code
Applying statistical learning theory to deep learning
Although statistical learning theory provides a robust framework to understand supervised learning, many theoretical aspects of deep learning remain unclear, in particular how different architectures may lead to inductive bias when trained using gradient based methods.
Langevin Monte Carlo for strongly log-concave distributions: Randomized midpoint revisited
To provide a more thorough explanation of our method for establishing the computable upper bound, we conduct an analysis of the midpoint discretization for the vanilla Langevin process.
ELF: Federated Langevin Algorithms with Primal, Dual and Bidirectional Compression
Federated sampling algorithms have recently gained great popularity in the community of machine learning and statistics.
Convergence of Stein Variational Gradient Descent under a Weaker Smoothness Condition
Stein Variational Gradient Descent (SVGD) is an important alternative to the Langevin-type algorithms for sampling from probability distributions of the form $\pi(x) \propto \exp(-V(x))$.
Penalized Langevin dynamics with vanishing penalty for smooth and log-concave targets
An upper bound on the Wasserstein-2 distance between the distribution of the PLD at time $t$ and the target is established.
Bounding the error of discretized Langevin algorithms for non-strongly log-concave targets
The error of sampling is measured by Wasserstein-$q$ distances.
