Zobrazeno 1 - 10
of 3 275
pro vyhledávání: '"A. Oko"'
We study the computational and sample complexity of learning a target function $f_*:\mathbb{R}^d\to\mathbb{R}$ with additive structure, that is, $f_*(x) = \frac{1}{\sqrt{M}}\sum_{m=1}^M f_m(\langle x, v_m\rangle)$, where $f_1,f_2,...,f_M:\mathbb{R}\t
Externí odkaz:
http://arxiv.org/abs/2406.11828
We study the problem of gradient descent learning of a single-index target function $f_*(\boldsymbol{x}) = \textstyle\sigma_*\left(\langle\boldsymbol{x},\boldsymbol{\theta}\rangle\right)$ under isotropic Gaussian data in $\mathbb{R}^d$, where the lin
Externí odkaz:
http://arxiv.org/abs/2406.01581
Flow matching (FM) has gained significant attention as a simulation-free generative model. Unlike diffusion models, which are based on stochastic differential equations, FM employs a simpler approach by solving an ordinary differential equation with
Externí odkaz:
http://arxiv.org/abs/2405.20879
In this paper, we extend mean-field Langevin dynamics to minimax optimization over probability distributions for the first time with symmetric and provably convergent updates. We propose mean-field Langevin averaged gradient (MFL-AG), a single-loop a
Externí odkaz:
http://arxiv.org/abs/2312.01127
Autor:
Inostroza-Pino, Natalia, Lattanzi, Valerio, Palmer, C. Zachary, Fortenberry, Ryan C., Mardones, Diego, Caselli, Paola, Godwin, Oko E., Lee, Timothy J.
The synergy between high-resolution rotational spectroscopy and quantum-chemical calculations is essential for exploring future detection of molecules, especially when spectroscopy parameters are not available yet. By using highly correlated ab initi
Externí odkaz:
http://arxiv.org/abs/2311.09063
Starches are important energy sources found in plants with many uses in the pharmaceutical industry such as binders, disintegrants, bulking agents in drugs and thus require very careful physicochemical analysis for proper identification and verificat
Externí odkaz:
http://arxiv.org/abs/2305.05321
The entropic fictitious play (EFP) is a recently proposed algorithm that minimizes the sum of a convex functional and entropy in the space of measures -- such an objective naturally arises in the optimization of a two-layer neural network in the mean
Externí odkaz:
http://arxiv.org/abs/2303.02957
While efficient distribution learning is no doubt behind the groundbreaking success of diffusion modeling, its theoretical guarantees are quite limited. In this paper, we provide the first rigorous analysis on approximation and generalization abiliti
Externí odkaz:
http://arxiv.org/abs/2303.01861
Publikováno v:
International Journal of Innovative Science and Research Technology , 2020
A composite log suite that comprised of gamma ray, resistivity, density and neutron logs of six wells (Agate, Diamond, Apatite, Calcite, Copper and Jasper) were employed to evaluate the petrophysical properties of the reservoirs of interest in XY fie
Externí odkaz:
http://arxiv.org/abs/2212.10852
While variance reduction methods have shown great success in solving large scale optimization problems, many of them suffer from accumulated errors and, therefore, should periodically require the full gradient computation. In this paper, we present a
Externí odkaz:
http://arxiv.org/abs/2209.00361