English
Related papers

Related papers: Exploring the Frontiers of Softmax: Provable Optim…

200 papers

This paper aims to understand the training solution, which is obtained by the back-propagation algorithm, of two-layer neural networks whose hidden layer is composed of the units with smooth activation functions, including the usual sigmoid…

Machine Learning · Computer Science 2025-07-22 Changcun Huang

The two-stage fine-tuning (FT) method, linear probing (LP) then fine-tuning (LP-FT), outperforms linear probing and FT alone. This holds true for both in-distribution (ID) and out-of-distribution (OOD) data. One key reason for its success…

Machine Learning · Computer Science 2024-10-23 Akiyoshi Tomihari , Issei Sato

We theoretically discuss why deep neural networks (DNNs) performs better than other models in some cases by investigating statistical properties of DNNs for non-smooth functions. While DNNs have empirically shown higher performance than…

Machine Learning · Statistics 2018-07-10 Masaaki Imaizumi , Kenji Fukumizu

Neural Tangent Kernel (NTK) is widely used to analyze overparametrized neural networks due to the famous result by Jacot et al. (2018): in the infinite-width limit, the NTK is deterministic and constant during training. However, this result…

Machine Learning · Computer Science 2022-07-22 Mariia Seleznova , Gitta Kutyniok

Statistical language models are central to many applications that use semantics. Recurrent Neural Networks (RNN) are known to produce state of the art results for language modelling, outperforming their traditional n-gram counterparts in…

Computation and Language · Computer Science 2016-02-05 Anantharaman Palacode Narayana Iyer

The remarkable ability of transformers to learn new concepts solely by reading examples within the input prompt, termed in-context learning (ICL), is a crucial aspect of intelligent behavior. Here, we focus on understanding the learning…

Machine Learning · Computer Science 2025-10-14 Sara Dragutinović , Andrew M. Saxe , Aaditya K. Singh

The Transformer architecture consists of self-attention and feed-forward networks (FFNs) which can be viewed as key-value memories according to previous works. However, FFN and traditional memory utilize different activation functions…

Computation and Language · Computer Science 2023-02-14 Kai Shen , Junliang Guo , Xu Tan , Siliang Tang , Rui Wang , Jiang Bian

Softmax is widely used in deep learning to map some representation to a probability distribution. As it is based on exp/log functions that are relatively expensive in multi-party computation, Mohassel and Zhang (2017) proposed a simpler…

Machine Learning · Computer Science 2021-07-07 Marcel Keller , Ke Sun

Deep neural networks (DNNs), particularly those using Rectified Linear Unit (ReLU) activation functions, have achieved remarkable success across diverse machine learning tasks, including image recognition, audio processing, and language…

Machine Learning · Computer Science 2026-03-26 Emi Zeger , Mert Pilanci

Large language models (LLMs) have brought significant and transformative changes in human society. These models have demonstrated remarkable capabilities in natural language understanding and generation, leading to various advancements and…

Machine Learning · Computer Science 2023-07-06 Yeqi Gao , Zhao Song , Shenghao Xie

Non-local (NL) block is a popular module that demonstrates the capability to model global contexts. However, NL block generally has heavy computation and memory costs, so it is impractical to apply the block to high-resolution feature maps.…

Computer Vision and Pattern Recognition · Computer Science 2022-07-28 Yooshin Cho , Youngsoo Kim , Hanbyel Cho , Jaesung Ahn , Hyeong Gwon Hong , Junmo Kim

We investigate the approximation efficiency of score functions by deep neural networks in diffusion-based generative modeling. While existing approximation theories utilize the smoothness of score functions, they suffer from the curse of…

Machine Learning · Computer Science 2023-09-21 Song Mei , Yuchen Wu

The softmax function is widely used in artificial neural networks for the multiclass classification problems, where the softmax transformation enforces the output to be positive and sum to one, and the corresponding loss function allows to…

Machine Learning · Computer Science 2021-12-24 Shaoshi Sun , Zhenyuan Zhang , BoCheng Huang , Pengbin Lei , Jianlin Su , Shengfeng Pan , Jiarun Cao

Conventional diffusion models typically relies on a fixed forward process, which implicitly defines complex marginal distributions over latent variables. This can often complicate the reverse process' task in learning generative…

Machine Learning · Statistics 2025-06-10 Grigory Bartosh , Dmitry Vetrov , Christian A. Naesseth

Normalization is a vital process for any machine learning task as it controls the properties of data and affects model performance at large. The impact of particular forms of normalization, however, has so far been investigated in limited…

Machine Learning · Computer Science 2022-06-22 Chintan Trivedi , Konstantinos Makantasis , Antonios Liapis , Georgios N. Yannakakis

While deep learning has outperformed other methods for various tasks, theoretical frameworks that explain its reason have not been fully established. To address this issue, we investigate the excess risk of two-layer ReLU neural networks in…

Machine Learning · Statistics 2022-06-07 Shunta Akiyama , Taiji Suzuki

Neural machine translation (NMT) models are typically trained using a softmax cross-entropy loss where the softmax distribution is compared against smoothed gold labels. In low-resource scenarios, NMT models tend to over-fit because the…

Computation and Language · Computer Science 2020-09-22 Raj Dabre , Atsushi Fujita

It has become standard to solve NLP tasks by fine-tuning pre-trained language models (LMs), especially in low-data settings. There is minimal theoretical understanding of empirical success, e.g., why fine-tuning a model with $10^8$ or more…

Machine Learning · Computer Science 2023-06-07 Sadhika Malladi , Alexander Wettig , Dingli Yu , Danqi Chen , Sanjeev Arora

One major task of spoken language understanding (SLU) in modern personal assistants is to extract semantic concepts from an utterance, called slot filling. Although existing slot filling models attempted to improve extracting new concepts…

Artificial Intelligence · Computer Science 2020-10-19 Yilin Shen , Wenhu Chen , Hongxia Jin

The proliferation of deep learning in natural language processing (NLP) has led to the development and release of innovative technologies capable of understanding and generating human language with remarkable proficiency. Atinuke, a…

Computation and Language · Computer Science 2024-02-06 Abiodun Finbarrs Oketunji