paper-with-me

Papers

Sparse Backpropagation for MoE Training

2023-10-01 · Liyuan Liu, Jianfeng Gao, Weizhu Chen

One defining characteristic of Mixture-of-Expert (MoE) models is their capacity for conducting sparse computation via expert routing, leading to remarkable scalability. However, backpropagation, the cornerstone of deep learning, requires dense computation, thereby posting challenges in MoE gradient computations. Here, we introduce SparseMixer, a scalable gradient estimator that bridges the gap between backpropagation and sparse expert routing. Unlike typical MoE training which strategically neglects certain gradient terms for the sake of sparse computation and scalability, SparseMixer provides scalable gradient approximations for these terms, enabling reliable gradient estimation in MoE training. Grounded in a numerical ODE framework, SparseMixer harnesses the mid-point method, a second-order ODE solver, to deliver precise gradient approximations with negligible computational overhead. Applying SparseMixer to Switch Transformer on both pre-training and machine translation tasks, SparseMixer showcases considerable performance gain, accelerating training convergence up to 2 times.

📄 PDF Abstract BibTeX arXiv:2310.00811

Code (0)

등록된 구현이 없습니다.

Tasks

Machine Translation

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Adam 설명 없음
Switch FFN A Switch FFN is a sparse layer that operates independently on tokens within an input sequence. It is shown in the blue block in the figure. We diagram two tokens ($x\_{1}$ =…

Similar Papers 제목 키워드 기반

TinyProp -- Adaptive Sparse Backpropagation for Efficient TinyML On-device Learning

2023-08-17 · Marcus Rüb, Daniel Maier, Daniel Mueller-Gritschneder, Axel Sikora

Training deep neural networks using backpropagation is very memory and computationally intensive. This makes it difficult to run on-device learning or fine-tune neural networks on tiny, embedded devices such as low-power…

SparseProp: Efficient Sparse Backpropagation for Faster Training of Neural Networks

2023-02-09 · Mahdi Nikdan, Tommaso Pegolotti, Eugenia Iofinova, Eldar Kurtic 외

We provide a new efficient version of the backpropagation algorithm, specialized to the case where the weights of the neural network being trained are sparse. Our algorithm is general, as it applies to arbitrary (unstruc…

Transfer Learning

A Practical Sparse Approximation for Real Time Recurrent Learning

2020-06-12 · Jacob Menick, Erich Elsen, Utku Evci, Simon Osindero 외

Current methods for training recurrent neural networks are based on backpropagation through time, which requires storing a complete history of network states, and prohibits updating the weights `online' (after every time…

Practical Real Time Recurrent Learning with a Sparse Approximation

2021-01-01 · ICLR 2021 1 · Jacob Menick, Erich Elsen, Utku Evci, Simon Osindero 외

Recurrent neural networks are usually trained with backpropagation through time, which requires storing a complete history of network states, and prohibits updating the weights "online" (after every timestep). Real Time …

Memorized Sparse Backpropagation

2019-05-24 · Zhiyuan Zhang, Pengcheng Yang, Xuancheng Ren, Qi Su 외

Neural network learning is usually time-consuming since backpropagation needs to compute full gradients and backpropagate them across multiple layers. Despite its success of existing works in accelerating propagation thr…