Zobrazeno 1 - 10
of 1 781
pro vyhledávání: '"Cohen, Samuel A"'
We propose a novel framework for exploring generalization errors of transfer learning through the lens of differential calculus on the space of probability measures. In particular, we consider two main transfer learning scenarios, $\alpha$-ERM and fi
Externí odkaz:
http://arxiv.org/abs/2410.17128
Autor:
Aminian, Gholamali, Asadi, Amir R., Li, Tian, Beirami, Ahmad, Reinert, Gesine, Cohen, Samuel N.
The generalization error (risk) of a supervised statistical learning algorithm quantifies its prediction ability on previously unseen data. Inspired by exponential tilting, Li et al. (2021) proposed the tilted empirical risk as a non-linear risk metr
Externí odkaz:
http://arxiv.org/abs/2409.19431
This work provides a theoretical framework for assessing the generalization error of graph neural networks in the over-parameterized regime, where the number of parameters surpasses the quantity of data points. We explore two widely utilized types of
Externí odkaz:
http://arxiv.org/abs/2402.07025
We consider a problem of stochastic optimal control with separable drift uncertainty in strong formulation on a finite horizon. The drift coefficient of the state $Y^{u}$ is multiplicatively influenced by an unknown random variable $\lambda$, while a
Externí odkaz:
http://arxiv.org/abs/2309.07091
Autor:
Cohen, Samuel N., Fausti, Eliana
This paper gives a self-contained introduction to the Hilbert projective metric $\mathcal{H}$ and its fundamental properties, with a particular focus on the space of probability measures. We start by defining the Hilbert pseudo-metric on convex cones
Externí odkaz:
http://arxiv.org/abs/2309.02413
Publikováno v:
NeurIPS Workshop on Optimal Transport and Machine Learning, 2021
Imitation learning (IL) seeks to teach agents specific tasks through expert demonstrations. One of the key approaches to IL is to define a distance between agent and expert and to find an agent policy that minimizes that distance. Optimal transport m
Externí odkaz:
http://arxiv.org/abs/2307.10810
We propose a novel framework for exploring weak and $L_2$ generalization errors of algorithms through the lens of differential calculus on the space of probability measures. Specifically, we consider the KL-regularized empirical risk minimization pro
Externí odkaz:
http://arxiv.org/abs/2306.11623
Autor:
Cohen, Samuel N., Lui, Silvia, Malpass, Will, Mantoan, Giulia, Nesheim, Lars, de Paula, Áureo, Reeves, Andrew, Scott, Craig, Small, Emma, Yang, Lingyi
Key economic variables are often published with a significant delay of over a month. The nowcasting literature has arisen to provide fast, reliable estimates of delayed economic indicators and is closely related to filtering methods in signal process
Externí odkaz:
http://arxiv.org/abs/2305.10256
Numerically solving high-dimensional partial differential equations (PDEs) is a major challenge. Conventional methods, such as finite difference methods, are unable to solve high-dimensional PDEs due to the curse-of-dimensionality. A variety of deep
Externí odkaz:
http://arxiv.org/abs/2305.06000
Autor:
Cohen, Samuel N., Fausti, Eliana
We consider the problem of estimating the state of a continuous-time Markov chain from noisy observations. We show that the corresponding optimal filter is strictly contracting pathwise, when considered in the Hilbert projective space, and give expli
Externí odkaz:
http://arxiv.org/abs/2305.02256