English
Related papers

Related papers: Your Transformer is Secretly Linear

200 papers

We show the effectiveness of automatic differentiation in efficiently and correctly computing and controlling the spectrum of implicitly linear operators, a rich family of layer types including all standard convolutional and dense layers.…

Machine Learning · Computer Science 2024-10-08 Ali Ebrahimpour Boroojeny , Matus Telgarsky , Hari Sundaram

While much work has been devoted to understanding the implicit (and explicit) regularization of deep nonlinear networks in the supervised setting, this paper focuses on unsupervised learning, i.e., autoencoders are trained with the…

Machine Learning · Computer Science 2021-10-25 Harald Steck , Dario Garcia Garcia

Large language models (LLMs) based on transformer are witnessing a notable trend of size expansion, which brings considerable costs to both model training and inference. However, existing methods such as model quantization, knowledge…

Computation and Language · Computer Science 2024-10-16 Yifei Yang , Zouying Cao , Hai Zhao

Current transformer language models are trained with uniform computational budgets across all layers, implicitly assuming layer homogeneity. We challenge this assumption through empirical analysis of SmolLM2-135M, a 30-layer, 135M-parameter…

Machine Learning · Computer Science 2026-03-23 Tomasz Wietrzykowski

Depth pruning improves the inference efficiency of large language models by removing Transformer blocks. Prior work typically treats layer redundancy as an inherent structural property of pretrained networks, emphasizing importance criteria…

Machine Learning · Computer Science 2026-05-28 Minkyu Kim , Vincent-Daniel Yun , Youngrae Kim , Suin Cho , Woosang Lim , Sunwoo Lee

Graph Convolutional Networks (GCNs) and their variants have experienced significant attention and have become the de facto methods for learning graph representations. GCNs derive inspiration primarily from recent deep learning approaches,…

Machine Learning · Computer Science 2019-06-21 Felix Wu , Tianyi Zhang , Amauri Holanda de Souza , Christopher Fifty , Tao Yu , Kilian Q. Weinberger

We characterize the singular values of the linear transformation associated with a standard 2D multi-channel convolutional layer, enabling their efficient computation. This characterization also leads to an algorithm for projecting a…

Machine Learning · Computer Science 2019-03-07 Hanie Sedghi , Vineet Gupta , Philip M. Long

Error correction code is a major part of the communication physical layer, ensuring the reliable transfer of data over noisy channels. Recently, neural decoders were shown to outperform classical decoding techniques. However, the existing…

Machine Learning · Computer Science 2022-03-30 Yoni Choukroun , Lior Wolf

We introduce token-consistent stochastic layers in vision transformers, without causing any severe drop in performance. The added stochasticity improves network calibration, robustness and strengthens privacy. We use linear layers with…

Computer Vision and Pattern Recognition · Computer Science 2022-07-15 Nikola Popovic , Danda Pani Paudel , Thomas Probst , Luc Van Gool

Low-rank approximations, of the weight and feature space can enhance the performance of deep learning models, whether in terms of improving generalization or reducing the latency of inference. However, there is no clear consensus yet on…

Computation and Language · Computer Science 2024-05-24 Arnav Chavan , Nahush Lele , Deepak Gupta

Training Large Language Models (LLMs) at ultra-low precision is critically impeded by instability rooted in the conflict between discrete quantization constraints and the intrinsic heavy-tailed spectral nature of linguistic data. By…

Machine Learning · Computer Science 2026-02-03 Junlin Huang , Wenyi Fang , Zhenheng Tang , Yuxin Wang , Xueze Kang , Yang Zheng , Bo Li , Xiaowen Chu

Overparametrized transformer networks are the state-of-the-art architecture for Large Language Models (LLMs). However, such models contain billions of parameters making large compute a necessity, while raising environmental concerns. To…

Machine Learning · Computer Science 2024-10-22 Yang Zhang , Yawei Li , Xinpeng Wang , Qianli Shen , Barbara Plank , Bernd Bischl , Mina Rezaei , Kenji Kawaguchi

In decoding linear block codes, it was shown that noticeable reliability gains can be achieved by introducing learnable parameters to the Belief Propagation (BP) decoder. Despite the success of these methods, there are two key open…

Information Theory · Computer Science 2023-04-13 Sravan Kumar Ankireddy , Hyeji Kim

We study how a one-layer attention-only transformer develops relevant structures while learning to sort lists of numbers. At the end of training, the model organizes its attention heads in two main modes that we refer to as…

Machine Learning · Computer Science 2025-02-03 Einar Urdshals , Jasmina Urdshals

In the context of classification problems, Deep Learning (DL) approaches represent state of art. Many DL approaches are based on variations of standard multi-layer feed-forward neural networks. These are also referred to as deep networks.…

Machine Learning · Computer Science 2023-11-21 Andrea Apicella , Francesco Isgrò , Roberto Prevete

Linear autoencoder models learn an item-to-item weight matrix via convex optimization with L2 regularization and zero-diagonal constraints. Despite their simplicity, they have shown remarkable performance compared to sophisticated…

Information Retrieval · Computer Science 2023-05-23 Jaewan Moon , Hye-young Kim , Jongwuk Lee

Transductive tasks on graphs differ fundamentally from typical supervised machine learning tasks, as the independent and identically distributed (i.i.d.) assumption does not hold among samples. Instead, all train/test/validation samples are…

Machine Learning · Computer Science 2024-11-21 Hamed Shirzad , Honghao Lin , Ameya Velingker , Balaji Venkatachalam , David Woodruff , Danica Sutherland

Transformer architecture has become the de-facto model for many machine learning tasks from natural language processing and computer vision. As such, improving its computational efficiency becomes paramount. One of the major computational…

Computation and Language · Computer Science 2022-05-17 Yue Guan , Zhengyi Li , Jingwen Leng , Zhouhan Lin , Minyi Guo

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

Large language models (LLMs) have shown remarkable capabilities in language understanding and generation. However, such impressive capability typically comes with a substantial model size, which presents significant challenges in deployment…

Computation and Language · Computer Science 2025-06-26 Guinan Su , Li Shen , Lu Yin , Shiwei Liu , Yanwu Yang , Jonas Geiping