English
Related papers

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

200 papers

We study the role of depth in training randomly initialized overparameterized neural networks. We give a general result showing that depth improves trainability of neural networks by improving the conditioning of certain kernel matrices of…

Machine Learning · Computer Science 2021-02-18 Naman Agarwal , Pranjal Awasthi , Satyen Kale

An increasingly popular machine learning paradigm is to pretrain a neural network (NN) on many tasks offline, then adapt it to downstream tasks, often by re-training only the last linear layer of the network. This approach yields strong…

Machine Learning · Computer Science 2024-06-10 Liam Collins , Hamed Hassani , Mahdi Soltanolkotabi , Aryan Mokhtari , Sanjay Shakkottai

Under mild conditions on the network initialization we derive a power series expansion for the Neural Tangent Kernel (NTK) of arbitrarily deep feedforward networks in the infinite width limit. We provide expressions for the coefficients of…

Machine Learning · Computer Science 2023-03-02 Michael Murray , Hui Jin , Benjamin Bowman , Guido Montufar

Neural networks are known for their ability to approximate smooth functions, yet they fail to generalize perfectly to unseen inputs when trained on discrete operations. Such operations lie at the heart of algorithmic tasks such as…

Machine Learning · Computer Science 2026-02-03 Artur Back de Luca , George Giapitzakis , Kimon Fountoulakis

Deep learning models are crucial for autonomous vehicle perception, but their reliability is challenged by algorithmic limitations and hardware faults. We address the latter by examining fault-tolerance in semantic segmentation models.…

Computer Vision and Pattern Recognition · Computer Science 2024-09-02 Leonardo Iurada , Niccolò Cavagnero , Fernando Fernandes Dos Santos , Giuseppe Averta , Paolo Rech , Tatiana Tommasi

Loss functions play a key role in training superior deep neural networks. In convolutional neural networks (CNNs), the popular cross entropy loss together with softmax does not explicitly guarantee minimization of intra-class variance or…

Computer Vision and Pattern Recognition · Computer Science 2019-04-26 XiaoBin Li , WeiQiang Wang

In this article, we review the literature on statistical theories of neural networks from three perspectives: approximation, training dynamics and generative models. In the first part, results on excess risks for neural networks are…

Machine Learning · Statistics 2024-09-17 Namjoon Suh , Guang Cheng

Activation sparsity is an intriguing property of deep neural networks that has been extensively studied in ReLU-based models, due to its advantages for efficiency, robustness, and interpretability. However, methods relying on exact zero…

Recently, neural tangent kernel (NTK) has been used to explain the dynamics of learning parameters of neural networks, at the large width limit. Quantitative analyses of NTK give rise to network widths that are often impractical and incur…

Machine Learning · Computer Science 2022-10-11 Nir Ailon , Supratim Shit

Solving non-convex, NP-hard optimization problems is crucial for training machine learning models, including neural networks. However, non-convexity often leads to black-box machine learning models with unclear inner workings. While convex…

Machine Learning · Computer Science 2025-03-18 Karthik Prakhya , Tolga Birdal , Alp Yurtsever

The remarkable success of large language models (LLMs) stems from their ability to consolidate vast amounts of knowledge into the memory during pre-training and to retrieve it from the memory during inference, enabling advanced capabilities…

Computation and Language · Computer Science 2025-10-10 Shaohua Zhang , Yuan Lin , Hang Li

While random Fourier features are a classic tool in kernel methods, their utility as a pre-processing step for deep learning on tabular data has been largely overlooked. Motivated by shortcomings in tabular deep learning pipelines -…

Machine Learning · Computer Science 2025-06-04 Renat Sergazinov , Jing Wu , Shao-An Yin

We propose an approximate strategy to efficiently train neural network based language models over very large vocabularies. Our approach, called adaptive softmax, circumvents the linear dependency on the vocabulary size by exploiting the…

Computation and Language · Computer Science 2017-06-20 Edouard Grave , Armand Joulin , Moustapha Cissé , David Grangier , Hervé Jégou

With the prevalence of large-scale pretrained vision-language models (VLMs), such as CLIP, soft-prompt tuning has become a popular method for adapting these models to various downstream tasks. However, few works delve into the inherent…

Computer Vision and Pattern Recognition · Computer Science 2024-08-28 Shuai Fu , Xiequn Wang , Qiushi Huang , Yu Zhang

Class Activation Mapping (CAM) and its extensions have become indispensable tools for visualizing the evidence behind deep network predictions. However, by relying on a final softmax classifier, these methods suffer from two fundamental…

Computer Vision and Pattern Recognition · Computer Science 2025-11-11 Yoojin Oh , Junhyug Noh

We propose a diffusion-based framework for prompt optimization that leverages Diffusion Language Models (DLMs) to iteratively refine system prompts through masked denoising. By conditioning on interaction traces, including user queries,…

Computation and Language · Computer Science 2026-02-24 Shiyu Wang , Haolin Chen , Liangwei Yang , Jielin Qiu , Rithesh Murthy , Ming Zhu , Zixiang Chen , Silvio Savarese , Caiming Xiong , Shelby Heinecke , Huan Wang

Sequence modeling is currently dominated by causal transformer architectures that use softmax self-attention. Although widely adopted, transformers require scaling memory and compute linearly during inference. A recent stream of work…

We improve the effectiveness of propagation- and linear-optimization-based neural network verification algorithms with a new tightened convex relaxation for ReLU neurons. Unlike previous single-neuron relaxations which focus only on the…

Machine Learning · Computer Science 2020-10-26 Christian Tjandraatmadja , Ross Anderson , Joey Huchette , Will Ma , Krunal Patel , Juan Pablo Vielma

Existing approaches to explaining deep learning models in NLP usually suffer from two major drawbacks: (1) the main model and the explaining model are decoupled: an additional probing or surrogate model is used to interpret an existing…

Computation and Language · Computer Science 2020-12-10 Zijun Sun , Chun Fan , Qinghong Han , Xiaofei Sun , Yuxian Meng , Fei Wu , Jiwei Li

Neural collapse (NC) describes the structured geometry that emerges in the features and weights of trained classifiers. Recent theory suggests NC can be suboptimal in deep architectures, attributing this to an explicit low-rank bias from L2…

Machine Learning · Computer Science 2026-05-25 Connall Garrod , Jonathan P. Keating , Christos Thrampoulidis