paper-with-me

홈 › Papers

Stochastic Optimization for Deep CCA via Nonlinear Orthogonal Iterations

2015-10-07 · Weiran Wang, Raman Arora, Karen Livescu, Nathan Srebro

Deep CCA is a recently proposed deep neural network extension to the traditional canonical correlation analysis (CCA), and has been successful for multi-view representation learning in several domains. However, stochastic optimization of the deep CCA objective is not straightforward, because it does not decouple over training examples. Previous optimizers for deep CCA are either batch-based algorithms or stochastic optimization using large minibatches, which can have high memory consumption. In this paper, we tackle the problem of stochastic optimization for deep CCA with small minibatches, based on an iterative solution to the CCA objective, and show that we can achieve as good performance as previous optimizers and thus alleviate the memory requirement.

📄 PDF Abstract BibTeX arXiv:1510.02054

Code (0)

등록된 구현이 없습니다.

Tasks

Representation LearningStochastic Optimization

Similar Papers 제목 키워드 기반

PowerSGD: Powered Stochastic Gradient Descent Methods for Accelerated Non-Convex Optimization

2019-09-25 · Jun Liu, Beitong Zhou, Weigao Sun, Ruijuan Chen 외

In this paper, we propose a novel technique for improving the stochastic gradient descent (SGD) method to train deep networks, which we term \emph{PowerSGD}. The proposed PowerSGD method simply raises the stochastic grad…

Infeasible Deterministic, Stochastic, and Variance-Reduction Algorithms for Optimization under Orthogonality Constraints

2023-03-29 · Pierre Ablin, Simon Vary, Bin Gao, P. -A. Absil

Orthogonality constraints naturally appear in many machine learning problems, from principal component analysis to robust neural network training. They are usually solved using Riemannian optimization algorithms, which m…

Riemannian optimization

Escaping From Saddle Points --- Online Stochastic Gradient for Tensor Decomposition

2015-03-06 · Rong Ge, Furong Huang, Chi Jin, Yang Yuan

We analyze stochastic gradient descent for optimizing non-convex functions. In many cases for non-convex functions the goal is to find a reasonable local minimum, and the main concern is that gradient updates are trapped…

Tensor Decomposition

Model-Driven Policy Optimization in Differentiable Simulators via Stochastic Exploration

2026-05-08 · Yuval Aroosh, Ayal Taitler arxiv

Differentiable planning enables gradient-based optimization of decision-making problems by leveraging differentiable models of system dynamics. However, in highly nonlinear and hybrid discrete-continuous domains, the res…

Nonlinear Two-Time-Scale Stochastic Approximation: Convergence and Finite-Time Performance

2020-11-03 · Thinh T. Doan

Two-time-scale stochastic approximation, a generalized version of the popular stochastic approximation, has found broad applications in many areas including stochastic control, optimization, and machine learning. Despite…

Vocal Bursts Valence Prediction