English
Related papers

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

200 papers

Parameter-Efficient Fine-Tuning (PEFT) is a popular class of techniques that strive to adapt large models in a scalable and resource-efficient manner. Yet, the mechanisms underlying their training performance and generalization remain…

Machine Learning · Computer Science 2026-02-10 Zahra Rahimi Afzal , Tara Esmaeilbeig , Mojtaba Soltanalian , Mesrob I. Ohannessian

The layered structure of deep neural networks hinders the use of numerous analysis tools and thus the development of its interpretability. Inspired by the success of functional brain networks, we propose a novel framework for…

Machine Learning · Computer Science 2022-05-25 Ben Zhang , Zhetong Dong , Junsong Zhang , Hongwei Lin

Deep convolutional neural networks (CNNs) trained with logistic and softmax losses have made significant advancement in visual recognition tasks in computer vision. When training data exhibit class imbalances, the class-wise reweighted…

Machine Learning · Computer Science 2020-03-06 Xiangrui Li , Xin Li , Deng Pan , Dongxiao Zhu

In-Context Learning and Chain-of-Thought prompting improve reasoning in large language models (LLMs). These typically come at the cost of longer, more expensive prompts that may contain redundant information. Prompt compression based on…

Computation and Language · Computer Science 2026-04-09 Caleb Zheng , Jyotika Singh , Fang Tu , Weiyi Sun , Sujeeth Bharadwaj , Yassine Benajiba , Sujith Ravi , Eli Shlizerman , Dan Roth

In the era of large language models (LLMs), fine-tuning pretrained models has become ubiquitous. Yet the theoretical underpinning remains an open question. A central question is why only a few epochs of fine-tuning are typically sufficient…

Machine Learning · Statistics 2026-02-17 Zexuan Sun , Garvesh Raskutti

We perform a study on the generalization ability of the wide two-layer ReLU neural network on $\mathbb{R}$. We first establish some spectral properties of the neural tangent kernel (NTK): $a)$ $K_{d}$, the NTK defined on $\mathbb{R}^{d}$,…

Machine Learning · Statistics 2023-02-14 Jianfa Lai , Manyun Xu , Rui Chen , Qian Lin

Large transformer models have achieved state-of-the-art results in numerous natural language processing tasks. Among the pivotal components of the transformer architecture, the attention mechanism plays a crucial role in capturing token…

Computation and Language · Computer Science 2026-03-16 Yichuan Deng , Zhao Song , Kaijun Yuan , Tianyi Zhou

This paper focuses on over-parameterized deep neural networks (DNNs) with ReLU activation functions and proves that when the data distribution is well-separated, DNNs can achieve Bayes-optimal test error for classification while obtaining…

Machine Learning · Computer Science 2023-06-01 Zhenyu Zhu , Fanghui Liu , Grigorios G Chrysos , Francesco Locatello , Volkan Cevher

The Neural Tangent Kernel (NTK) framework explains optimization in over-parameterized neural networks via approximately linearized dynamics, yielding exponential convergence guarantees. However, existing results are often overly pessimistic…

Machine Learning · Computer Science 2026-05-26 Ruchirinkil Marreddy , Chaoyue Liu

A major factor in the success of deep neural networks is the use of sophisticated architectures rather than the classical multilayer perceptron (MLP). Residual networks (ResNets) stand out among these powerful modern architectures. Previous…

Machine Learning · Computer Science 2021-05-25 Tom Tirer , Joan Bruna , Raja Giryes

While transformer models exhibit strong in-context learning (ICL) abilities, they often fail to generalize under simple distribution shifts. We analyze these failures and identify Softmax, the scoring function in the attention mechanism, as…

Computation and Language · Computer Science 2026-05-12 Omar Naim , Swarnadeep Bhar , Jérôme Bolte , Nicholas Asher

We introduce a cumulant-expansion framework for quantifying how large language models (LLMs) internalize higher-order statistical structure during next-token prediction. By treating the softmax entropy of each layer's logit distribution as…

Computation and Language · Computer Science 2025-10-07 Karthik Viswanathan , Sang Eon Park

Softmax is the de facto standard in modern neural networks for language processing when it comes to normalizing logits. However, by producing a dense probability distribution each token in the vocabulary has a nonzero chance of being…

Computation and Language · Computer Science 2022-05-20 Maxat Tezekbayev , Vassilina Nikoulina , Matthias Gallé , Zhenisbek Assylbekov

In state-of-the-art deep learning for object recognition, SoftMax and Sigmoid functions are most commonly employed as the predictor outputs. Such layers often produce overconfident predictions rather than proper probabilistic scores, which…

Computer Vision and Pattern Recognition · Computer Science 2022-05-13 Gledson Melotti , Cristiano Premebida , Jordan J. Bird , Diego R. Faria , Nuno Gonçalves

Transformers have improved drastically the performance of natural language processing (NLP) and computer vision applications. The computation of transformers involves matrix multiplications and non-linear activation functions such as…

Hardware Architecture · Computer Science 2024-02-19 Christodoulos Peltekis , Kosmas Alexandridis , Giorgos Dimitrakopoulos

We develop a solvable model of neural scaling laws beyond the kernel limit. Theoretical analysis of this model shows how performance scales with model size, training time, and the total amount of available data. We identify three scaling…

Machine Learning · Statistics 2025-04-07 Blake Bordelon , Alexander Atanasov , Cengiz Pehlevan

As its width tends to infinity, a deep neural network's behavior under gradient descent can become simplified and predictable (e.g. given by the Neural Tangent Kernel (NTK)), if it is parametrized appropriately (e.g. the NTK…

Machine Learning · Computer Science 2022-07-18 Greg Yang , Edward J. Hu

We study training one-hidden-layer ReLU networks in the neural tangent kernel (NTK) regime, where the networks' biases are initialized to some constant rather than zero. We prove that under such initialization, the neural network will have…

Machine Learning · Computer Science 2024-10-31 Hongru Yang , Ziyu Jiang , Ruizhe Zhang , Yingbin Liang , Zhangyang Wang

It is often remarked that neural networks fail to increase their uncertainty when predicting on data far from the training distribution. Yet naively using softmax confidence as a proxy for uncertainty achieves modest success in tasks…

Machine Learning · Computer Science 2021-06-10 Tim Pearce , Alexandra Brintrup , Jun Zhu

For certain infinitely-wide neural networks, the neural tangent kernel (NTK) theory fully characterizes generalization, but for the networks used in practice, the empirical NTK only provides a rough first-order approximation. Still, a…

Machine Learning · Computer Science 2021-10-14 Guillermo Ortiz-Jiménez , Seyed-Mohsen Moosavi-Dezfooli , Pascal Frossard
‹ Prev 1 4 5 6 7 8 10 Next ›