Zobrazeno 1 - 10
of 4 758
pro vyhledávání: '"Wright, Stephen A."'
Autor:
Dickens, Charles, Pryor, Connor, Gao, Changyu, Albalak, Alon, Augustine, Eriq, Wang, William, Wright, Stephen, Getoor, Lise
The field of Neural-Symbolic (NeSy) systems is growing rapidly. Proposed approaches show great promise in achieving symbiotic unions of neural and symbolic methods. However, each NeSy system differs in fundamental ways. There is a pressing need for a
Externí odkaz:
http://arxiv.org/abs/2407.09693
We revisit the problem of federated learning (FL) with private data from people who do not trust the server or other silos/clients. In this context, every silo (e.g. hospital) has data from several people (e.g. patients) and needs to protect the priv
Externí odkaz:
http://arxiv.org/abs/2407.09690
Autor:
Smucker, Byran J., Wright, Stephen E., Williams, Isaac, Page, Richard C., Kiss, Andor J., Silwal, Surendra Bikram, Weese, Maria, Edwards, David J.
High-throughput screening, in which multiwell plates are used to test large numbers of compounds against specific targets, is widely used across many areas of the biological sciences and most prominently in drug discovery. We propose a statistically
Externí odkaz:
http://arxiv.org/abs/2407.06173
Autor:
Li, Shuyao, Cheng, Yu, Diakonikolas, Ilias, Diakonikolas, Jelena, Ge, Rong, Wright, Stephen J.
Finding an approximate second-order stationary point (SOSP) is a well-studied and fundamental problem in stochastic nonconvex optimization with many applications in machine learning. However, this problem is poorly understood in the presence of outli
Externí odkaz:
http://arxiv.org/abs/2403.10547
We provide a simple and flexible framework for designing differentially private algorithms to find approximate stationary points of non-convex loss functions. Our framework is based on using a private approximate risk minimizer to "warm start" anothe
Externí odkaz:
http://arxiv.org/abs/2402.11173
Publikováno v:
Proceedings of the International Conference on Machine Learning (ICML) 2024
We focus on constrained, $L$-smooth, potentially stochastic and nonconvex-nonconcave min-max problems either satisfying $\rho$-cohypomonotonicity or admitting a solution to the $\rho$-weakly Minty Variational Inequality (MVI), where larger values of
Externí odkaz:
http://arxiv.org/abs/2402.05071
We leverage convex and bilevel optimization techniques to develop a general gradient-based parameter learning framework for neural-symbolic (NeSy) systems. We demonstrate our framework with NeuPSL, a state-of-the-art NeSy architecture. To achieve thi
Externí odkaz:
http://arxiv.org/abs/2401.09651
Optimal experimental design (OED) aims to choose the observations in an experiment to be as informative as possible, according to certain statistical criteria. In the linear case (when the observations depend linearly on the unknown parameters), it s
Externí odkaz:
http://arxiv.org/abs/2401.07806
Autor:
Alacaoglu, Ahmet, Wright, Stephen J.
We analyze the complexity of single-loop quadratic penalty and augmented Lagrangian algorithms for solving nonconvex optimization problems with functional equality constraints. We consider three cases, in all of which the objective is stochastic and
Externí odkaz:
http://arxiv.org/abs/2311.00678
A randomized algorithm for nonconvex minimization with inexact evaluations and complexity guarantees
Autor:
Li, Shuyao, Wright, Stephen J.
We consider minimization of a smooth nonconvex function with inexact oracle access to gradient and Hessian (without assuming access to the function value) to achieve approximate second-order optimality. A novel feature of our method is that if an app
Externí odkaz:
http://arxiv.org/abs/2310.18841