English
Related papers

Related papers: SUS backprop: linear backpropagation algorithm for…

200 papers

Large transformer models have shown extraordinary success in achieving state-of-the-art results in many natural language processing applications. However, training and deploying these models can be prohibitively costly for long sequences,…

Machine Learning · Computer Science 2020-06-16 Sinong Wang , Belinda Z. Li , Madian Khabsa , Han Fang , Hao Ma

The attention operator is arguably the key distinguishing factor of transformer architectures, which have demonstrated state-of-the-art performance on a variety of tasks. However, transformer attention operators often impose a significant…

Machine Learning · Computer Science 2024-12-24 Ziyang Wu , Tianjiao Ding , Yifu Lu , Druv Pai , Jingyuan Zhang , Weida Wang , Yaodong Yu , Yi Ma , Benjamin D. Haeffele

Standard inference and training with transformer based architectures scale quadratically with input sequence length. This is prohibitively large for a variety of applications especially in web-page translation, query-answering etc.…

Computation and Language · Computer Science 2023-03-20 Lovish Madaan , Srinadh Bhojanapalli , Himanshu Jain , Prateek Jain

Motivated by the factorization inherent in the original fast multipole method and the improved fast Gauss transform we introduce a factorable form of attention that operates efficiently in high dimensions. This approach reduces the…

Machine Learning · Computer Science 2024-02-13 Armin Gerami , Monte Hoover , Pranav S. Dulepet , Ramani Duraiswami

In modern neural networks like Transformers, linear layers require significant memory to store activations during backward pass. This study proposes a memory reduction approach to perform backpropagation through linear layers. Since the…

Machine Learning · Computer Science 2022-02-04 Daniel Bershatsky , Aleksandr Mikhalev , Alexandr Katrutsa , Julia Gusak , Daniil Merkulov , Ivan Oseledets

Deep learning employs multi-layer neural networks trained via the backpropagation algorithm. This approach has achieved success across many domains and relies on adaptive gradient methods such as the Adam optimizer. Sequence modeling…

Machine Learning · Computer Science 2025-07-16 Esmail Gumaan

As software projects rapidly evolve, software artifacts become more complex and defects behind get harder to identify. The emerging Transformer-based approaches, though achieving remarkable performance, struggle with long code sequences due…

Software Engineering · Computer Science 2024-09-13 Xueqi Yang , Mariusz Jakubowski , Li Kang , Haojie Yu , Tim Menzies

Gradient descent has been a central training principle for artificial neural networks from the early beginnings to today's deep learning networks. The most common implementation is the backpropagation algorithm for training feed-forward…

Machine Learning · Computer Science 2020-06-09 Stefan Jaeger

The original softmax-based attention mechanism (regular attention) in the extremely successful Transformer architecture computes attention between $N$ tokens, each embedded in a $D$-dimensional head, with a time complexity of $O(N^2D)$.…

Machine Learning · Computer Science 2025-10-28 Armin Gerami , Ramani Duraiswami

Transformers have proven highly effective across modalities, but standard softmax attention scales quadratically with sequence length, limiting long context modeling. Linear attention mitigates this by approximating attention with kernel…

Machine Learning · Computer Science 2026-02-10 Ashkan Shahbazi , Chayne Thrash , Yikun Bai , Keaton Hamm , Navid NaderiAlizadeh , Soheil Kolouri

Transformers' quadratic complexity with respect to the input sequence length has motivated a body of work on efficient sparse approximations to softmax. An alternative path, used by entmax transformers, consists of having built-in exact…

Computation and Language · Computer Science 2022-04-22 Marcos Treviso , António Góis , Patrick Fernandes , Erick Fonseca , André F. T. Martins

The transformer architecture has driven breakthroughs in recent years on tasks which require modeling pairwise relationships between sequential elements, as is the case in natural language understanding. However, long seqeuences pose a…

Computation and Language · Computer Science 2024-03-26 Heejun Lee , Jina Kim , Jeffrey Willette , Sung Ju Hwang

Self-attention has recently been adopted for a wide range of sequence modeling problems. Despite its effectiveness, self-attention suffers from quadratic compute and memory requirements with respect to sequence length. Successful approaches…

Machine Learning · Computer Science 2020-10-27 Aurko Roy , Mohammad Saffar , Ashish Vaswani , David Grangier

The self-attention mechanism has been a key factor in the advancement of vision Transformers. However, its quadratic complexity imposes a heavy computational burden in high-resolution scenarios, restricting the practical application.…

Computer Vision and Pattern Recognition · Computer Science 2025-12-29 Dongchen Han , Tianyu Li , Ziyi Wang , Gao Huang

Deep neural networks have evolved to become power demanding and consequently difficult to apply to small-size mobile platforms. Network parameter reduction methods have been introduced to systematically deal with the computational and…

Computer Vision and Pattern Recognition · Computer Science 2020-05-12 Mahdi Biparva , John Tsotsos

Transformer-based models are widely used in natural language processing (NLP). Central to the transformer model is the self-attention mechanism, which captures the interactions of token pairs in the input sequences and depends quadratically…

Machine Learning · Computer Science 2021-11-19 Zhanpeng Zeng , Yunyang Xiong , Sathya N. Ravi , Shailesh Acharya , Glenn Fung , Vikas Singh

We propose a simple yet effective technique for neural network learning. The forward propagation is computed as usual. In back propagation, only a small subset of the full gradient is computed to update the model parameters. The gradient…

Machine Learning · Computer Science 2019-03-12 Xu Sun , Xuancheng Ren , Shuming Ma , Houfeng Wang

With the rapid growth in model size, fine-tuning the large pre-trained language model has become increasingly difficult due to its extensive memory usage. Previous works usually focus on reducing the number of trainable parameters in the…

We propose a novel approach to reduce memory consumption of the backpropagation through time (BPTT) algorithm when training recurrent neural networks (RNNs). Our approach uses dynamic programming to balance a trade-off between caching of…

Neural and Evolutionary Computing · Computer Science 2016-06-13 Audrūnas Gruslys , Remi Munos , Ivo Danihelka , Marc Lanctot , Alex Graves

Sparse training is a natural idea to accelerate the training speed of deep neural networks and save the memory usage, especially since large modern neural networks are significantly over-parameterized. However, most of the existing methods…

Machine Learning · Computer Science 2021-11-11 Xiao Zhou , Weizhong Zhang , Zonghao Chen , Shizhe Diao , Tong Zhang