Zobrazeno 1 - 10
of 187
pro vyhledávání: '"Lu, Zhaosong"'
In this paper, we study a class of deterministically constrained stochastic optimization problems. Existing methods typically aim to find an $\epsilon$-stochastic stationary point, where the expected violations of both constraints and first-order sta
Externí odkaz:
http://arxiv.org/abs/2409.09906
In this paper, we study a class of non-smooth non-convex problems in the form of $\min_{x}[\max_{y\in Y}\phi(x, y) - \max_{z\in Z}\psi(x, z)]$, where both $\Phi(x) = \max_{y\in Y}\phi(x, y)$ and $\Psi(x)=\max_{z\in Z}\psi(x, z)$ are weakly convex fun
Externí odkaz:
http://arxiv.org/abs/2405.18577
Autor:
He, Chuan, Lu, Zhaosong
In this paper we consider a nonconvex unconstrained optimization problem minimizing a twice differentiable objective function with H\"older continuous Hessian. Specifically, we first propose a Newton-conjugate gradient (Newton-CG) method for finding
Externí odkaz:
http://arxiv.org/abs/2311.13094
Publikováno v:
Journal of Machine Learning Research, Volume 24, No. 166, pp. 1-34, 2023
In this paper we consider a composite optimization problem that minimizes the sum of a weakly smooth function and a convex function with either a bounded domain or a uniformly convex structure. In particular, we first present a parameter-dependent co
Externí odkaz:
http://arxiv.org/abs/2305.18181
Various optimal gradient-based algorithms have been developed for smooth nonconvex optimization. However, many nonconvex machine learning problems do not belong to the class of smooth functions and therefore the existing algorithms are sub-optimal. I
Externí odkaz:
http://arxiv.org/abs/2303.02854
In this paper we consider finding an approximate second-order stationary point (SOSP) of general nonconvex conic optimization that minimizes a twice differentiable function subject to nonlinear equality constraints and also a convex conic constraint.
Externí odkaz:
http://arxiv.org/abs/2301.04204
In this paper we consider finding a second-order stationary point (SOSP) of nonconvex equality constrained optimization when a nearly feasible point is known. In particular, we first propose a new Newton-CG method for finding an approximate SOSP of u
Externí odkaz:
http://arxiv.org/abs/2301.03139
Autor:
Lu, Zhaosong, Mei, Sanyou
In this paper we study a class of constrained minimax problems. In particular, we propose a first-order augmented Lagrangian method for solving them, whose subproblems turn out to be a much simpler structured minimax problem and are suitably solved b
Externí odkaz:
http://arxiv.org/abs/2301.02060
Autor:
Lu, Zhaosong, Mei, Sanyou
In this paper we study a class of unconstrained and constrained bilevel optimization problems in which the lower level is a possibly nonsmooth convex optimization problem, while the upper level is a possibly nonconvex optimization problem. We introdu
Externí odkaz:
http://arxiv.org/abs/2301.01716
Autor:
He, Chuan, Lu, Zhaosong
In this paper we consider finding an approximate second-order stationary point (SOSP) of nonconvex conic optimization that minimizes a twice differentiable function over the intersection of an affine subspace and a convex cone. In particular, we prop
Externí odkaz:
http://arxiv.org/abs/2207.05697