Global Convergence of Langevin Dynamics Based Algorithms for Nonconvex Optimization
نویسندگان
چکیده
We present a unified framework to analyze the global convergence of Langevin dynamics based algorithms for nonconvex finite-sum optimization with n component functions. At the core of our analysis is a direct analysis of the ergodicity of the numerical approximations to Langevin dynamics, which leads to faster convergence rates. Specifically, we show that gradient Langevin dynamics (GLD) and stochastic gradient Langevin dynamics (SGLD) converge to the almost minimizer within Õ ( nd/(λ ) ) 2 and Õ ( d/(λ ) ) stochastic gradient evaluations respectively, where d is the problem dimension, and λ is the spectral gap of the Markov chain generated by GLD. Both of the results improve upon the best known gradient complexity results (Raginsky et al., 2017). Furthermore, for the first time we prove the global convergence guarantee for variance reduced stochastic gradient Langevin dynamics (VR-SGLD) (Dubey et al., 2016) to the almost minimizer after Õ (√ nd/(λ ) ) stochastic gradient evaluations, which outperforms the gradient complexities of GLD and SGLD in a wide regime. Our theoretical analyses shed some light on using Langevin dynamics based algorithms for nonconvex optimization with provable guarantees.
منابع مشابه
Quasi-Newton Methods for Nonconvex Constrained Multiobjective Optimization
Here, a quasi-Newton algorithm for constrained multiobjective optimization is proposed. Under suitable assumptions, global convergence of the algorithm is established.
متن کاملOn the Global Convergence of Majorization Minimization Algorithms for Nonconvex Optimization Problems
In this paper, we study the global convergence of majorization minimization (MM) algorithms for solving nonconvex regularized optimization problems. MM algorithms have received great attention in machine learning. However, when applied to nonconvex optimization problems, the convergence of MM algorithms is a challenging issue. We introduce theory of the KurdykaLojasiewicz inequality to address ...
متن کاملModify the linear search formula in the BFGS method to achieve global convergence.
<span style="color: #333333; font-family: Calibri, sans-serif; font-size: 13.3333px; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-weight: 400; letter-spacing: normal; orphans: 2; text-align: justify; text-indent: 0px; text-transform: none; white-space: normal; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; background-color: #ffffff; text-dec...
متن کاملOnline ICA: Understanding Global Dynamics of Nonconvex Optimization via Diffusion Processes
Solving statistical learning problems often involves nonconvex optimization. Despite the empirical success of nonconvex statistical optimization methods, their global dynamics, especially convergence to the desirable local minima, remain less well understood in theory. In this paper, we propose a new analytic paradigm based on diffusion processes to characterize the global dynamics of nonconvex...
متن کاملEfficient random coordinate descent algorithms for large-scale structured nonconvex optimization
In this paper we analyze several new methods for solving nonconvex optimization problems with the objective function formed as a sum of two terms: one is nonconvex and smooth, and another is convex but simple and its structure is known. Further, we consider both cases: unconstrained and linearly constrained nonconvex problems. For optimization problems of the above structure, we propose random ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید
ثبت ناماگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید
ورودعنوان ژورنال:
- CoRR
دوره abs/1707.06618 شماره
صفحات -
تاریخ انتشار 2017