2 citations · 7 across the 18 of their papers we have counts for
23 papers
Expert Coupling in MoE Pretraining: Reducing All-to-All Overhead with Correlated Placement and Token Shuffling
Radha Gulhane, Quentin Anthony, Beren Millidge
Mixture-of-Experts (MoE) layers replace the feed-forward block of a Transformer with E expert networks, and each token is routed to k of these experts. Under expert parallelism (EP…
An inverse-stochastic-control Galerkin estimator for drift potentials
Yumiharu Nakano
We consider the ill-posed inverse problem of recovering the drift potential of an overdamped Langevin diffusion from discrete, possibly irregular position observations. Specializin…
Kernel-based potential mean-field games with unbiased random Fourier -statistics
Yumiharu Nakano
We study the subclass of potential mean-field games in which the running interaction cost and the terminal target cost are both expressed through reproducing-kernel maximum mean di…
Continuum-marginal optimal transport: a mesh-free kernel method
Yumiharu Nakano
In this paper we study continuum-marginal optimal transport. Given a time-continuous family of probability marginals, the problem is to recover the minimum-energy velocity field wh…
Inverse Stochastic Control via Generalized Schrödinger Problems
Yumiharu Nakano
We propose a variational formulation of an inverse problem in continuous-time stochastic control, aimed at identifying control costs consistent with a given distribution over traje…
A deep learning approach to multi-marginal optimal transport via Hilbert space embeddings of probability measures
Yumiharu Nakano, Takafumi Saito
We propose a numerical method for solving the multi-marginal Monge problem, which extends the classical Monge formulation to settings involving multiple target distributions. Our a…