English
Related papers

Related papers: Depth-Adaptive Transformer

200 papers

Despite the widespread adoption of Transformer models for NLP tasks, the expressive power of these models is not well-understood. In this paper, we establish that Transformer models are universal approximators of continuous permutation…

Machine Learning · Computer Science 2020-02-26 Chulhee Yun , Srinadh Bhojanapalli , Ankit Singh Rawat , Sashank J. Reddi , Sanjiv Kumar

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

Pre-trained Transformer models like T5 and BART have advanced the state of the art on a wide range of text generation tasks. Compressing these models into smaller ones has become critically important for practical use. Common neural network…

Computation and Language · Computer Science 2023-06-06 Wangchunshu Zhou , Ronan Le Bras , Yejin Choi

Large Transformer models yield impressive results on many tasks, but are expensive to train, or even fine-tune, and so slow at decoding that their use and study becomes out of reach. We address this problem by leveraging sparsity. We study…

Pre-trained Large Language Models (LLMs) encapsulate large amounts of knowledge and take enormous amounts of compute to train. We make use of this resource, together with the observation that LLMs are able to transfer knowledge and…

Machine Learning · Computer Science 2025-01-14 Malcolm L. Wolff , Shenghao Yang , Kari Torkkola , Michael W. Mahoney

Most neural networks utilize the same amount of compute for every example independent of the inherent complexity of the input. Further, methods that adapt the amount of computation to the example focus on finding a fixed inference-time…

Machine Learning · Computer Science 2020-04-17 Ankur Bapna , Naveen Arivazhagan , Orhan Firat

Transliteration is a key component of machine translation systems and software internationalization. This paper demonstrates that neural sequence-to-sequence models obtain state of the art or close to state of the art results on existing…

Computation and Language · Computer Science 2016-11-01 Mihaela Rosca , Thomas Breuel

Recent research has demonstrated that transformers, particularly linear attention models, implicitly execute gradient-descent-like algorithms on data provided in-context during their forward inference step. However, their capability in…

Machine Learning · Computer Science 2024-10-31 Max Vladymyrov , Johannes von Oswald , Mark Sandler , Rong Ge

We show that a constant number of self-attention layers can efficiently simulate, and be simulated by, a constant number of communication rounds of Massively Parallel Computation. As a consequence, we show that logarithmic depth is…

Machine Learning · Computer Science 2024-02-15 Clayton Sanford , Daniel Hsu , Matus Telgarsky

Even though convolutional neural networks have become the method of choice in many fields of computer vision, they still lack interpretability and are usually designed manually in a cumbersome trial-and-error process. This paper aims at…

Computer Vision and Pattern Recognition · Computer Science 2019-12-12 Maria Ximena Bastidas Rodriguez , Adrien Gruson , Luisa F. Polania , Shin Fujieda , Flavio Prieto Ortiz , Kohei Takayama , Toshiya Hachisuka

Transformers have become the dominant architecture for sequence modeling tasks such as natural language processing or audio processing, and they are now even considered for tasks that are not naturally sequential such as image…

Machine Learning · Computer Science 2024-03-05 Jorg Bornschein , Yazhe Li , Amal Rannen-Triki

Transformers excel at in-context learning (ICL) -- learning from demonstrations without parameter updates -- but how they do so remains a mystery. Recent work suggests that Transformers may internally run Gradient Descent (GD), a…

Machine Learning · Computer Science 2024-11-19 Deqing Fu , Tian-Qi Chen , Robin Jia , Vatsal Sharan

The standard neural machine translation model can only decode with the same depth configuration as training. Restricted by this feature, we have to deploy models of various sizes to maintain the same translation latency, because the…

Computation and Language · Computer Science 2020-10-19 Qiang Wang , Tong Xiao , Jingbo Zhu

Typical deep learning approaches to modeling high-dimensional data often result in complex models that do not easily reveal a new understanding of the data. Research in the deep learning field is very actively pursuing new methods to…

Machine Learning · Computer Science 2022-05-16 Charles Anderson , Jason Stock , David Anderson

Deep learning models are widely used across computer vision and other domains. When working on the model induction, selecting the right architecture for a given dataset often relies on repetitive trial-and-error procedures. This procedure…

Machine Learning · Computer Science 2026-01-06 Yen-Chia Chen , Hsing-Kuo Pao , Hanjuan Huang

How do we perform efficient inference while retaining high translation quality? Existing neural machine translation models, such as Transformer, achieve high performance, but they decode words one by one, which is inefficient. Recent…

Computation and Language · Computer Science 2021-10-15 Chenyang Huang , Hao Zhou , Osmar R. Zaïane , Lili Mou , Lei Li

Transformers have proven highly effective across various applications, especially in handling sequential data such as natural languages and time series. However, transformer models often lack clear interpretability, and the success of…

Machine Learning · Computer Science 2025-12-01 Wei Shi , Yuan Cao

Can transformers generalize efficiently on problems that require dealing with examples with different levels of difficulty? We introduce a new task tailored to assess generalization over different complexities and present results that…

In-context learning refers to the ability of a model to condition on a prompt sequence consisting of in-context examples (input-output pairs corresponding to some task) along with a new query input, and generate the corresponding output.…

Computation and Language · Computer Science 2023-08-15 Shivam Garg , Dimitris Tsipras , Percy Liang , Gregory Valiant

Large Transformer models routinely achieve state-of-the-art results on a number of tasks but training these models can be prohibitively costly, especially on long sequences. We introduce two techniques to improve the efficiency of…

Machine Learning · Computer Science 2020-02-19 Nikita Kitaev , Łukasz Kaiser , Anselm Levskaya