English
Related papers

Related papers: Enhanced QKNorm normalization for neural transform…

200 papers

We present a novel framework to overcome the limitations of equivariant architectures in learning functions with group symmetries. In contrary to equivariant architectures, we use an arbitrary base model such as an MLP or a transformer and…

Machine Learning · Computer Science 2024-04-16 Jinwoo Kim , Tien Dat Nguyen , Ayhan Suleymanzade , Hyeokjun An , Seunghoon Hong

The current standard architecture of Large Language Models (LLMs) with QKV self-attention is briefly summarized, including the architecture of a typical Transformer. Scaling laws for compute (flops) and memory (parameters plus data) are…

General Literature · Computer Science 2025-11-18 William H. Press

This paper presents an simple yet sophisticated approach to the challenge by Sproat and Jaitly (2016)- given a large corpus of written text aligned to its normalized spoken form, train an RNN to learn the correct normalization function.…

Computation and Language · Computer Science 2017-12-20 Maryam Zare , Shaurya Rohatgi

Normalization techniques have become a basic component in modern convolutional neural networks (ConvNets). In particular, many recent works demonstrate that promoting the orthogonality of the weights helps train deep models and improve…

Computer Vision and Pattern Recognition · Computer Science 2022-01-05 Sheng Liu , Xiao Li , Yuexiang Zhai , Chong You , Zhihui Zhu , Carlos Fernandez-Granda , Qing Qu

Data augmentation is one of the most popular techniques for improving the robustness of neural networks. In addition to directly training the model with original samples and augmented samples, a torrent of methods regularizing the distance…

Machine Learning · Computer Science 2020-11-30 Haohan Wang , Zeyi Huang , Xindi Wu , Eric P. Xing

Normalizing flows are a popular class of models for approximating probability distributions. However, their invertible nature limits their ability to model target distributions whose support have a complex topological structure, such as…

Machine Learning · Statistics 2022-02-25 Vincent Stimper , Bernhard Schölkopf , José Miguel Hernández-Lobato

Training stability of large language models(LLMs) is an important research topic. Reproducing training instabilities can be costly, so we use a small language model with 830M parameters and experiment with higher learning rates to force…

Computation and Language · Computer Science 2024-10-23 Oleg Rybakov , Mike Chrzanowski , Peter Dykas , Jinze Xue , Ben Lanir

This paper proposes an active learning method for designing experiments to identify quasi-Linear Parameter-Varying (qLPV) models. Since informative experiments are costly, input signals must be selected to maximize information content based…

Systems and Control · Electrical Eng. & Systems 2025-12-08 Sampath Kumar Mulagaleti , Alberto Bemporad

Transformers are a widespread and successful model architecture, particularly in Natural Language Processing (NLP) and Computer Vision (CV). The essential innovation of this architecture is the Attention Mechanism, which solves the problem…

Machine Learning · Computer Science 2024-11-25 Bernhard Bermeitinger , Tomas Hrycej , Massimo Pavone , Julianus Kath , Siegfried Handschuh

In this paper, we consider the simplest version of a linear neural network (LNN). Assuming that for training (constructing an optimal weight matrix $Q$) we have a set of training pairs, i.e. we know the input data \begin{equation}…

Numerical Analysis · Mathematics 2024-08-12 S. Liu , S. I. Kabanikhin , S. V. Strijhak

Per-example gradient norms are a vital ingredient for estimating gradient noise scale (GNS) with minimal variance. Observing the tensor contractions required to compute them, we propose a method with minimal FLOPs in 3D or greater tensor…

Machine Learning · Computer Science 2024-11-05 Gavia Gray , Aman Tiwari , Shane Bergsma , Joel Hestness

Transformers have supplanted recurrent models in a large number of NLP tasks. However, the differences in their abilities to model different syntactic properties remain largely unknown. Past works suggest that LSTMs generalize very well on…

Computation and Language · Computer Science 2020-10-09 Satwik Bhattamishra , Kabir Ahuja , Navin Goyal

Modern reinforcement learning (RL) algorithms have found success by using powerful probabilistic models, such as transformers, energy-based models, and diffusion/flow-based models. To this end, RL researchers often choose to pay the price…

Machine Learning · Computer Science 2025-06-05 Raj Ghugare , Benjamin Eysenbach

This document aims to be a self-contained, mathematically precise overview of transformer architectures and algorithms (*not* results). It covers what transformers are, how they are trained, what they are used for, their key architectural…

Machine Learning · Computer Science 2022-07-26 Mary Phuong , Marcus Hutter

In recent years, a plethora of spectral graph neural networks (GNN) methods have utilized polynomial basis with learnable coefficients to achieve top-tier performances on many node-level tasks. Although various kinds of polynomial bases…

Machine Learning · Computer Science 2023-03-31 Qian Tao , Zhen Wang , Wenyuan Yu , Yaliang Li , Zhewei Wei

We introduce a Normalized Convolutional Neural Layer, a novel approach to normalization in convolutional networks. Unlike conventional methods, this layer normalizes the rows of the im2col matrix during convolution, making it inherently…

Computer Vision and Pattern Recognition · Computer Science 2025-04-03 Dongsuk Kim , Geonhee Lee , Myungjae Lee , Shin Uk Kang , Dongmin Kim

Normalization methods are a central building block in the deep learning toolbox. They accelerate and stabilize training, while decreasing the dependence on manually tuned learning rate schedules. When learning from multi-modal…

Machine Learning · Computer Science 2018-10-15 Lucas Deecke , Iain Murray , Hakan Bilen

Recent works have shown that transformers can solve contextual reasoning tasks by internally executing computational graphs called circuits. Circuits often use attention to logically match information from subspaces of the representation,…

Machine Learning · Computer Science 2024-06-27 Stephen Menary , Samuel Kaski , Andre Freitas

Normalization techniques have only recently begun to be exploited in supervised learning tasks. Batch normalization exploits mini-batch statistics to normalize the activations. This was shown to speed up training and result in better…

Machine Learning · Computer Science 2017-03-08 Mengye Ren , Renjie Liao , Raquel Urtasun , Fabian H. Sinz , Richard S. Zemel

Transformers have demonstrated effectiveness in in-context solving data-fitting problems from various (latent) models, as reported by Garg et al. However, the absence of an inherent iterative structure in the transformer architecture…

Machine Learning · Computer Science 2024-03-19 Liu Yang , Kangwook Lee , Robert Nowak , Dimitris Papailiopoulos