paper-with-me

Papers

AdaLoss: A computationally-efficient and provably convergent adaptive gradient method

2021-09-17 · Xiaoxia Wu, Yuege Xie, Simon Du, Rachel Ward

We propose a computationally-friendly adaptive learning rate schedule, "AdaLoss", which directly uses the information of the loss function to adjust the stepsize in gradient descent methods. We prove that this schedule enjoys linear convergence in linear regression. Moreover, we provide a linear convergence guarantee over the non-convex regime, in the context of two-layer over-parameterized neural networks. If the width of the first-hidden layer in the two-layer networks is sufficiently large (polynomially), then AdaLoss converges robustly \emph{to the global minimum} in polynomial time. We numerically verify the theoretical results and extend the scope of the numerical experiments by considering applications in LSTM models for text clarification and policy gradients for control problems.

📄 PDF Abstract BibTeX arXiv:2109.08282

Code (0)

등록된 구현이 없습니다.

Tasks

regression

Methods 이 논문이 사용한 방법론

Tanh Activation 설명 없음
Sigmoid Activation 설명 없음
LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…

Similar Papers 제목 키워드 기반

IntSGD: Adaptive Floatless Compression of Stochastic Gradients

2021-02-16 · ICLR 2022 4 · Konstantin Mishchenko, Bokun Wang, Dmitry Kovalev, Peter Richtárik

We propose a family of adaptive integer compression operators for distributed Stochastic Gradient Descent (SGD) that do not communicate a single float. This is achieved by multiplying floating-point vectors with a number…

Provably Convergent Two-Timescale Off-Policy Actor-Critic with Function Approximation

2019-11-11 · ICML 2020 1 · Shangtong Zhang, Bo Liu, Hengshuai Yao, Shimon Whiteson

We present the first provably convergent two-timescale off-policy actor-critic algorithm (COF-PAC) with function approximation. Key to COF-PAC is the introduction of a new critic, the emphasis critic, which is trained vi…

Vocal Bursts Valence Prediction

Proximal Quasi-Newton for Computationally Intensive L1-regularized M-estimators

2014-06-27 · NeurIPS 2014 12 · Kai Zhong, Ian E. H. Yen, Inderjit S. Dhillon, Pradeep Ravikumar

We consider the class of optimization problems arising from computationally intensive L1-regularized M-estimators, where the function or gradient values are very expensive to compute. A particular instance of interest is…

General ClassificationStructured Prediction

A Simple Guard for Learned Optimizers

2022-01-28 · Isabeau Prémont-Schwarz, Jaroslav Vítků, Jan Feyereisl

If the trend of learned components eventually outperforming their hand-crafted version continues, learned optimizers will eventually outperform hand-crafted optimizers like SGD or Adam. Even if learned optimizers (L2Os) …

Full Gradient DQN Reinforcement Learning: A Provably Convergent Scheme

2021-03-10 · K. E. Avrachenkov, V. S. Borkar, H. P. Dolhare, K. Patil

We analyze the DQN reinforcement learning algorithm as a stochastic approximation scheme using the o.d.e. (for 'ordinary differential equation') approach and point out certain theoretical issues. We then propose a modifi…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)