Float64 tests over five grids numerically verify the finite identities, mapped one-layer and recursive trajectories, conditioning predictions, and theorem-matched Adam separation of a controlled finite Brownian RKHS with nodal, increment, and spectral coordinates.
Abstract
Equivalent finite parameterizations can represent the same functions and intrinsic norm yet induce different optimization algorithms. We study this effect in a controlled finite Brownian RKHS with nodal, increment, and spectral coordinates. Classical finite-element, RKHS-interpolation, Brownian-covariance, and mixed-boundary DCT identities make the shared hypothesis class, Brownian energy, approximation operator, and coordinate maps explicit. Our main results concern the optimization geometry of this fixed model. With mapped initialization, identical scalar steps, and identical minibatches, nodal and spectral GD/SGD have exactly the same mapped trajectories. Increment GD is an explicit Euler step for the constant Brownian/Sobolev metric, with factor $1/h$. For Brownian-regularized least squares, $\kappa_2(\mathbf H_{\mathrm{inc}})\le1+A/\rho$, independently of grid resolution $G$ for fixed $A$, $\rho>0$, and the stated normalization. Under the stated standard-Adam convention, the universal orthogonal equivariance group is exactly the signed permutations; the block DCT-VIII transform is not one. Float64 tests over five grids numerically verify the finite identities, mapped one-layer and recursive trajectories, conditioning predictions, and theorem-matched Adam separation. Thus coordinate effects are isolated without changing the represented functions, intrinsic regularizer, or approximation space.
We prove a weighted Wasserstein spectral gap for the three-dimensional primitive equations on $\mathscr E=\{u\in H^1\cap L^8: \partial_zu\in L^4\}$ under finite-rank additive Brownian forcing that is phase-complete finite Fourier and satisfies a quantitative quadratic saturation condition. In particular, four real forc...
This work introduces the class $\mathcal{P}_\psi(\mu)$ of measures that differ from a reference measure only through a finite-dimensional map $\psi$ while preserving the reference conditionals on its fibers, and develops approximation theory for fitting within it.
R. Baptista, Bamdad Hosseini, Alexander Hsu· 0 citations
This work develops a general framework that separates score discretization from Brownian-motion simulation and allows multiple geodesic random-walk steps per score evaluation and provides a sharper characterization of the convergence and sampling complexity of Riemannian diffusion models.
We study infinite-dimensional Dyson Brownian motions obtained as limits of finite systems without rescaling the actual stochastic dynamics. For $\beta=2$, we construct determinantal processes on an extended space of initial data and prove convergence of their finite-dimensional distributions under essentially optimal c...
Claims about the benefit of depth depend on the complexity assigned to a representation. We introduce the \emph{Variation Brownian Kernel Ladder} (VBKL), a path-atomic function-space framework that separates nonlinear recursive dictionary construction from linear variation superposition. Starting from linear projection...
In this paper, we solve risk functional minimization problems with general losses in Banach spaces within the framework of stochastic approximation. We introduce an adaptive regularization strategy for stochastic mirror descent (SMD). Specifically, using a Schauder basis, we construct nested finite-dimensional subspace...
Jin-Hui Bai, Shuai Lu, Lei Shi· arXiv.org· 0 citations
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduNov 17, 2026
By studying the computational foundations of language learning, Associate Professor Jacob Andreas builds intelligent systems that can communicate effectively with humans.
Microsoft Research Blog· microsoft.comNov 16, 2026
AI coding agents are increasingly help developers fix bugs and build features largely on their own, but every interaction with their models consumes tokens. In each session, an agent sends instructions, tool descriptions, and session history to its model. Most efforts to reduce this cost focus on individual tasks. Yet developers return to the same […] The post TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient appeared first on Microsoft Research.
MIT News · Artificial Intelligence· news.mit.eduNov 13, 2026