Gradient Descent
Gradient Descent Meets Shift-and-Invert Preconditioning for Eigenvector Computation
Neural Information Processing Systems http://nips.cc/
Exact natural gradient in deep linear networks and its application to the nonlinear case
Alberto Bernacchia, Mate Lengyel, Guillaume Hennequin
Neural Information Processing Systems http://nips.cc/
Evolved Policy Gradients
Rein Houthooft, Yuhua Chen, Phillip Isola, Bradly Stadie, Filip Wolski, OpenAI Jonathan Ho, Pieter Abbeel
We propose a metalearning approach for learning gradient-based reinforcement learning (RL) algorithms.
Learning with SGD and Random Features
Luigi Carratino, Alessandro Rudi, Lorenzo Rosasco
Sketching and stochastic gradient methods are arguably the most common techniques to derive efficient large scale learning algorithms. In this paper, we investigate their application in the context of nonparametric statistical learning.
New Insight into Hybrid Stochastic Gradient Descent: Beyond With-Replacement Sampling and Convexity
Pan Zhou, Xiaotong Yuan, Jiashi Feng
As an incremental-gradient algorithm, the hybrid stochastic gradient descent (HS-GD) enjoys merits of both stochastic and full gradient methods for finite-sum problem optimization.
Connecting Optimization and Regularization Paths
Consequently, a line of work has focused on characterizing the implicit biases of global optimum reached by various optimization algorithms. For example, Gunasekar et al. [ 2017 ] consider the problem of matrix factorization and show that gradient descent (GD) on un-regularized objective converges to the minimum nuclear norm solution.
Evolutionary Stochastic Gradient Descent for Optimization of Deep Neural Networks
Xiaodong Cui, Wei Zhang, Zoltรกn Tรผske, Michael Picheny
The complementarity between SGD and EA is worth investigating.
Uncertainty Sampling is Preconditioned Stochastic Gradient Descent on Zero-One Loss
Stephen Mussmann, Percy S. Liang
Neural Information Processing Systems http://nips.cc/
On Learning Intrinsic Rewards for Policy Gradient Methods
Zeyu Zheng, Junhyuk Oh, Satinder Singh
In this paper we build on the Optimal Rewards Framework of Singh et al. [2010] that defines the optimal intrinsic reward function as one that when used by an RL agent achieves behavior that optimizes the
The Physical Systems Behind Optimization Algorithms
Lin Yang, Raman Arora, Vladimir braverman, Tuo Zhao
In particular, we study gradient descent, proximal gradient descent, coordinate gradient descent, proximal coordinate gradient, and Newton's methods as well as their Nesterov's accelerated variants in a unified framework motivated by a