Accelerating variance-reduced stochastic gradient methods
نویسندگان
چکیده
منابع مشابه
Riemannian stochastic variance reduced gradient
Stochastic variance reduction algorithms have recently become popular for minimizing the average of a large but finite number of loss functions. In this paper, we propose a novel Riemannian extension of the Euclidean stochastic variance reduced gradient algorithm (R-SVRG) to a manifold search space. The key challenges of averaging, adding, and subtracting multiple gradients are addressed with r...
متن کاملVariance Reduced Stochastic Gradient Descent with Neighbors
Stochastic Gradient Descent (SGD) is a workhorse in machine learning, yet it is also known to be slow relative to steepest descent. The variance in the stochastic update directions only allows for sublinear or (with iterate averaging) linear convergence rates. Recently, variance reduction techniques such as SVRG and SAGA have been proposed to overcome this weakness. With asymptotically vanishin...
متن کاملAccelerating Stochastic Gradient Descent using Predictive Variance Reduction
Stochastic gradient descent is popular for large scale optimization but has slow convergence asymptotically due to the inherent variance. To remedy this problem, we introduce an explicit variance reduction method for stochastic gradient descent which we call stochastic variance reduced gradient (SVRG). For smooth and strongly convex functions, we prove that this method enjoys the same fast conv...
متن کاملStochastic Variance-Reduced Hamilton Monte Carlo Methods
We propose a fast stochastic Hamilton Monte Carlo (HMC) method, for sampling from a smooth and strongly log-concave distribution. At the core of our proposed method is a variance reduction technique inspired by the recent advance in stochastic optimization. We show that, to achieve accuracy in 2-Wasserstein distance, our algorithm achieves Õ ( n+ κd/ + κdn/ 2/3 ) gradient complexity (i.e., numb...
متن کاملAccelerating Stochastic Gradient Descent
There is widespread sentiment that fast gradient methods (e.g. Nesterov’s acceleration, conjugate gradient, heavy ball) are not effective for the purposes of stochastic optimization due to their instability and error accumulation. Numerous works have attempted to quantify these instabilities in the face of either statistical or non-statistical errors (Paige, 1971; Proakis, 1974; Polyak, 1987; G...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Mathematical Programming
سال: 2020
ISSN: 0025-5610,1436-4646
DOI: 10.1007/s10107-020-01566-2