1 citations · 1 across the 11 of their papers we have counts for
14 papers
Any-Dimensional Invariant Universality
Shengtai Yao, Eitan Levin, Mateo Díaz
Several machine learning models are defined for inputs of any size, such as graphs with different numbers of nodes and point clouds containing varying numbers of points. The univer…
Nonsmooth Riemannian optimization with inexact manifold primitives via bundle methods
Mateo Díaz, Benjamin Grimmer, Ian McPherson
Optimization on Hadamard manifolds -- the natural Riemannian setting for globally geodesically convex problems -- relies on exponential maps to retract tangent vectors and parallel…
Active set identification and rapid convergence for degenerate primal-dual problems
Mateo Díaz, Pedro Izquierdo Lehmann, Haihao Lu +1
Primal-dual methods for solving convex optimization problems with functional constraints often exhibit a distinct two-stage behavior. Initially, they converge towards a solution at…
pscaling small models: Principled warm starts and hyperparameter transfer
Yuxin Ma, Nan Chen, Mateo Díaz +3
Modern large-scale neural networks are often trained and released in multiple sizes to accommodate diverse inference budgets. To improve efficiency, recent work has explored model…
Preconditioned subgradient method for composite optimization: overparameterization and fast convergence
Mateo Díaz, Liwei Jiang, Abdel Ghani Labassi
Composite optimization problems involve minimizing the composition of a smooth map with a convex function. Such objectives arise in numerous data science and signal processing appl…
Beyond Scores: Proximal Diffusion Models
Zhenghan Fang, Mateo Díaz, Sam Buchanan +1
Diffusion models have quickly become some of the most popular and powerful generative models for high-dimensional data. The key insight that enabled their development was the reali…
On Transferring Transferability: Towards a Theory for Size Generalization
Eitan Levin, Yuxin Ma, Mateo Díaz +1
Many modern learning tasks require models that can take inputs of varying sizes. Consequently, dimension-independent architectures have been proposed for domains where the inputs a…
Invariant Kernels: Rank Stabilization and Generalization Across Dimensions
Mateo Díaz, Dmitriy Drusvyatskiy, Jack Kendrick +1
Symmetry arises often when learning from high dimensional data. For example, data sets consisting of point clouds, graphs, and unordered sets appear routinely in contemporary appli…
PDLP: A Practical First-Order Method for Large-Scale Linear Programming
David Applegate, Mateo Díaz, Oliver Hinder +4
We present PDLP, a practical first-order method for linear programming (LP) designed to solve large-scale LP problems. PDLP is based on the primal-dual hybrid gradient (PDHG) metho…
The radius of statistical efficiency
Joshua Cutler, Mateo Díaz, Dmitriy Drusvyatskiy
Classical results in asymptotic statistics show that the Fisher information matrix controls the difficulty of estimating a statistical model from observed data. In this work, we in…
Controlling the False Discovery Rate in Subspace Selection
Mateo Díaz, Venkat Chandrasekaran
Controlling the false discovery rate (FDR) is a popular approach to multiple testing, variable selection, and related problems of simultaneous inference. In many contemporary appli…
Photometric follow-up of the 20 Myr-old multi-planet host star V1298~Tau with CHEOPS and ground-based telescopes
M. Damasso, G. Scandariato, V. Nascimbeni +25
V1298 Tau hosts at least four planets. Since its discovery, this system has been a target of intensive photometric and spectroscopic monitoring. The characterisation of its archite…
Any-dimensional equivariant neural networks
Eitan Levin, Mateo Díaz
Traditional supervised learning aims to learn an unknown mapping by fitting a function to a set of input-output pairs with a fixed dimension. The fitted function is then defined on…
Robust, randomized preconditioning for kernel ridge regression
Mateo Díaz, Ethan N. Epperly, Zachary Frangella +2
We investigate preconditioned conjugate gradient methods for kernel ridge regression (KRR) problems with a moderate to large number of data points (). We dev…