English
Related papers

Related papers: Transformers Provably Learn Sparse Token Selection…

200 papers

Transformers have the capacity to act as supervised learning algorithms: by properly encoding a set of labeled training ("in-context") examples and an unlabeled test example into an input sequence of vectors of the same dimension, the…

Machine Learning · Computer Science 2024-12-16 Spencer Frei , Gal Vardi

Deep learning has emerged as a compelling framework for scientific and engineering computing, motivating growing interest in neural network-based solvers for partial differential equations (PDEs). Within this landscape, network…

Numerical Analysis · Mathematics 2026-04-06 Tao Cheng , Lili Ju , Zhonghua Qiao , Xiaoping Zhang

Transformers have achieved great success in recent years. Interestingly, transformers have shown particularly strong in-context learning capability -- even without fine-tuning, they are still able to solve unseen tasks well purely based on…

Machine Learning · Computer Science 2024-11-19 Zihao Li , Yuan Cao , Cheng Gao , Yihan He , Han Liu , Jason M. Klusowski , Jianqing Fan , Mengdi Wang

To accelerate the training of graph convolutional networks (GCNs) on real-world large-scale sparse graphs, downsampling methods are commonly employed as a preprocessing step. However, the effects of graph sparsity and topological structure…

Machine Learning · Computer Science 2024-09-10 Qinji Shu , Hang Sheng , Feng Ji , Hui Feng , Bo Hu

When and how can an attention mechanism learn to selectively attend to informative tokens, thereby enabling detection of weak, rare, and sparsely located features? We address these questions theoretically in a sparse-token classification…

Machine Learning · Computer Science 2025-09-30 Nicholas Barnfield , Hugo Cui , Yue M. Lu

Transformers have impressive generalization capabilities on tasks with a fixed context length. However, they fail to generalize to sequences of arbitrary length, even for seemingly simple tasks such as duplicating a string. Moreover, simply…

Transformers have excelled in natural language modeling and one reason behind this success is their exceptional ability to combine contextual informal and global knowledge. However, the theoretical basis remains unclear. In this paper,…

Machine Learning · Computer Science 2024-11-01 Yunwei Ren , Zixuan Wang , Jason D. Lee

Transformers, adapted from natural language processing, are emerging as a leading approach for graph representation learning. Contemporary graph transformers often treat nodes or edges as separate tokens. This approach leads to…

Machine Learning · Computer Science 2023-10-04 Zihan Pengmei , Zimu Li , Chih-chan Tien , Risi Kondor , Aaron R. Dinner

In this work we introduce KERNELIZED TRANSFORMER, a generic, scalable, data driven framework for learning the kernel function in Transformers. Our framework approximates the Transformer kernel as a dot product between spectral feature maps…

Machine Learning · Computer Science 2022-07-22 Sankalan Pal Chowdhury , Adamos Solomou , Avinava Dubey , Mrinmaya Sachan

Although dominant in natural language processing, transformer-based models remain challenged by the task of long-sequence processing, because the computational cost of self-attention operations in transformers swells quadratically with the…

Computation and Language · Computer Science 2024-07-08 Jiawen Xie , Pengyu Cheng , Xiao Liang , Yong Dai , Nan Du

We provide novel guaranteed approaches for training feedforward neural networks with sparse connectivity. We leverage on the techniques developed previously for learning linear networks and show that they can also be effectively adopted to…

Machine Learning · Computer Science 2015-04-29 Hanie Sedghi , Anima Anandkumar

Prior-data fitted networks (PFNs) have recently emerged as a powerful approach for Bayesian prediction tasks, approximating the posterior predictive distribution (PPD) through in-context learning. Despite their strong empirical performance…

Machine Learning · Statistics 2026-05-27 Gyeonghun Kang , Changwoo J. Lee , Xiang Cheng

We study the training of Vision Transformers for semi-supervised image classification. Transformers have recently demonstrated impressive performance on a multitude of supervised learning tasks. Surprisingly, we show Vision Transformers…

Computer Vision and Pattern Recognition · Computer Science 2022-07-19 Zejia Weng , Xitong Yang , Ang Li , Zuxuan Wu , Yu-Gang Jiang

Hierarchical neural networks are exponentially more efficient than their corresponding "shallow" counterpart with the same expressive power, but involve huge number of parameters and require tedious amounts of training. By approximating the…

Machine Learning · Computer Science 2019-12-20 Bálint Daróczy , Rita Aleksziev , András Benczúr

Transformers lack an explicit architectural mechanism for storing and organizing knowledge acquired during training. We introduce learnable sparse memory banks: a set of latent tokens, randomly initialized and trained end-to-end, that…

Machine Learning · Computer Science 2026-03-24 Tasmay Pankaj Tibrewal , Pritish Saha , Ankit Meda , Kunal Singh , Pradeep Moturi

Transformers achieve state-of-the-art accuracy and robustness across many tasks, but an understanding of their inductive biases and how those biases differ from other neural network architectures remains elusive. In this work, we identify…

Machine Learning · Computer Science 2025-02-14 Bhavya Vasudeva , Deqing Fu , Tianyi Zhou , Elliott Kau , Youqi Huang , Vatsal Sharan

Standard transformer architectures apply the same number of layers to every token regardless of contextual difficulty. We present Token-Selective Attention (TSA), a learned per-token gate on residual updates between consecutive transformer…

Machine Learning · Computer Science 2026-05-08 Ahmed Abdelmuniem Abdalla Mohammed

Large neural networks are very successful in various tasks. However, with limited data, the generalization capabilities of deep neural networks are also very limited. In this paper, we empirically start showing that intrinsically sparse…

Neural and Evolutionary Computing · Computer Science 2019-06-28 Shiwei Liu , Decebal Constantin Mocanu , Mykola Pechenizkiy

Transfer learning leverages feature representations of deep neural networks (DNNs) pretrained on source tasks with rich data to empower effective finetuning on downstream tasks. However, the pretrained models are often prohibitively large…

Machine Learning · Computer Science 2025-01-07 Yonggan Fu , Ye Yuan , Shang Wu , Jiayi Yuan , Yingyan Celine Lin

A longstanding goal in the theory of deep learning is to characterize the conditions under which a given neural network architecture will be trainable, and if so, how well it might generalize to unseen data. In this work, we provide such a…

Machine Learning · Computer Science 2020-07-14 Lechao Xiao , Jeffrey Pennington , Samuel S. Schoenholz