Statistical Learning
Variance reduction for Random Coordinate Descent-Langevin Monte Carlo
There is vast literature on sampling, and proposed methods fall into a few different categories.
DiffPhyCon: A Generative Approach to Control Complex Physical Systems Long Wei
Classical techniques suffer from limited applicability or huge computational costs.
Provable Subspace Identification Under Post-Nonlinear Mixtures
UML is known to be challenging: Even learning linear mixtures requires highly nontrivial analytical tools, e.g., independent component analysis or nonnegative matrix factorization.
Efficient Contextual Bandits with Continuous Actions Maryam Majzoubi New York University Chicheng Zhang University of Arizona Rajan Chari
We create a computationally tractable algorithm for contextual bandits with continuous actions having unknown structure.
Asynchronous SGD Beats Minibatch SGD Under Arbitrary Delays
"virtual iterates" and delay-adaptive stepsizes, which allow us to derive state-of-the-art guarantees for both convex and non-convex objectives.
DrivAerNet++: A Large-Scale Multimodal Car Dataset with Computational Fluid Dynamics Simulations and Deep Learning Benchmarks
With more than 39 TB of publicly available engineering data, DrivAerNet++ fills a significant gap in available resources, providing high-quality, diverse data to enhance model training, promote generalization, and accelerate automotive design processes.