State space models (SSMs) have high performance on long sequence modeling but require
sophisticated initialization techniques and specialized implementations for high quality and …

Large neural networks excel in many domains, but they are expensive to train and fine-tune.
A popular approach to reduce their compute or memory requirements is to replace dense …

The class of random features is one of the most popular techniques to speed up kernel
methods in large-scale problems. Related works have been recognized by the NeurIPS Test …

Overparameterized neural networks generalize well but are expensive to train. Ideally, one
would like to reduce their computational cost while retaining their generalization benefits …

Large foundation models are becoming ubiquitous, but training them from scratch is
prohibitively expensive. Thus, efficiently adapting these powerful models to downstream …

Fast linear transforms are ubiquitous in machine learning, including the discrete Fourier
transform, discrete cosine transform, and other structured transformations such as …

Laplace approximation (LA) and its linearized variant (LLA) enable effortless adaptation of
pretrained deep neural networks to Bayesian neural networks. The generalized Gauss …

Learning the principal eigenfunctions of an integral operator defined by a kernel and a data
distribution is at the core of many machine learning problems. Traditional nonparametric …

Modern neural network architectures use structured linear transformations, such as low-rank
matrices, sparse matrices, permutations, and the Fourier transform, to improve inference …

We present Uni-Fusion, a universal continuous mapping framework for surfaces, surface
properties (color, infrared, etc.) and more (latent features in contrastive language-image …