English
Related papers

Related papers: Bug or Feature$^2$: Weight Drift, Activation Spars…

200 papers

This paper presents a unified mixed-integer programming framework for training sparse and interpretable neural networks. We develop exact formulations for both fully connected and convolutional architectures by modeling nonlinearities such…

Artificial Intelligence · Computer Science 2025-04-22 Masoud Ataei , Edrin Hasaj , Jacob Gipp , Sepideh Forouzi

Modern large language models (LLMs) have established state-of-the-art performance through architectural improvements, but still require significant computational cost for inference. In an effort to reduce the inference cost, post-training…

Computation and Language · Computer Science 2024-05-24 Jaewoo Yang , Hayun Kim , Younghoon Kim

ReLU neural-networks have been in the focus of many recent theoretical works, trying to explain their empirical success. Nonetheless, there is still a gap between current theoretical results and empirical observations, even in the case of…

Machine Learning · Computer Science 2019-06-13 Jonathan Fiat , Eran Malach , Shai Shalev-Shwartz

The loss function used to train a neural network is strongly connected to its output layer from a statistical point of view. This technical report analyzes common activation functions for a neural network output layer, like linear, sigmoid,…

Machine Learning · Computer Science 2025-11-10 Fernando Berzal

We present a novel methodology for repairing neural networks that use ReLU activation functions. Unlike existing methods that rely on modifying the weights of a neural network which can induce a global change in the function space, our…

Machine Learning · Computer Science 2022-07-25 Feisi Fu , Wenchao Li

We study the implicit bias of ReLU neural networks trained by a variant of SGD where at each step, the label is changed with probability $p$ to a random label (label smoothing being a close variant of this procedure). Our experiments…

Machine Learning · Computer Science 2021-11-04 Elisabetta Cornacchia , Jan Hązła , Ido Nachum , Amir Yehudayoff

This work studies the behavior of shallow ReLU networks trained with the logistic loss via gradient descent on binary classification data where the underlying data distribution is general, and the (optimal) Bayes risk is not necessarily…

Machine Learning · Computer Science 2021-11-05 Ziwei Ji , Justin D. Li , Matus Telgarsky

The Spiking Neural Network (SNN), a biologically inspired neural network infrastructure, has garnered significant attention recently. SNNs utilize binary spike activations for efficient information transmission, replacing multiplications…

Computer Vision and Pattern Recognition · Computer Science 2025-06-10 Yufei Guo , Yuhan Zhang , Zhou Jie , Xiaode Liu , Xin Tong , Yuanpei Chen , Weihang Peng , Zhe Ma

Dynamic Sparse Training (DST) methods achieve state-of-the-art results in sparse neural network training, matching the generalization of dense models while enabling sparse training and inference. Although the resulting models are highly…

Machine Learning · Computer Science 2024-02-23 Mike Lasby , Anna Golubeva , Utku Evci , Mihai Nica , Yani Ioannou

We derive a synaptic weight update rule for learning temporally precise spike train to spike train transformations in multilayer feedforward networks of spiking neurons. The framework, aimed at seamlessly generalizing error backpropagation…

Neural and Evolutionary Computing · Computer Science 2016-01-11 Arunava Banerjee

Weight decay is one of the most widely used forms of regularization in deep learning, and has been shown to improve generalization and robustness. The optimization objective driving weight decay is a sum of losses plus a term proportional…

Machine Learning · Computer Science 2023-07-07 Liu Yang , Jifan Zhang , Joseph Shenouda , Dimitris Papailiopoulos , Kangwook Lee , Robert D. Nowak

Network pruning is aimed at imposing sparsity in a neural network architecture by increasing the portion of zero-valued weights for reducing its size regarding energy-efficiency consideration and increasing evaluation speed. In most of the…

Machine Learning · Computer Science 2018-07-17 Amirsina Torfi , Rouzbeh A. Shirvani , Sobhan Soleymani , Nasser M. Nasrabadi

Despite the tremendous successes of deep neural networks (DNNs) in various applications, many fundamental aspects of deep learning remain incompletely understood, including DNN trainability. In a trainability study, one aims to discern what…

Machine Learning · Computer Science 2023-05-19 Yueyao Yu , Yin Zhang

We here study whether training biases can make hidden neurons specialize in minimal one-hidden-layer MLPs, and whether such specialization improves prototype-based reconstruction of the training dataset from the learned weights. We consider…

Machine Learning · Computer Science 2026-05-26 Enrique Alba , Ezequiel Lopez-Rubio

Large language models (LLMs) deliver strong performance but are difficult to deploy due to high memory and compute costs. While pruning reduces these demands, most methods ignore activation sparsity observed at runtime. We reinterpret…

Machine Learning · Computer Science 2025-11-14 Ruokai Yin , Yuhang Li , Donghyun Lee , Priyadarshini Panda

Deep neural networks owe their expressive power to nonlinear activation functions. The effective field theory of signal propagation at initialization reveals a few distinct universality classes of activations that exhibit different depth…

Disordered Systems and Neural Networks · Physics 2026-05-08 Omri Lesser , Debanjan Chowdhury

Neural network training is computationally and memory intensive. Sparse training can reduce the burden on emerging hardware platforms designed to accelerate sparse computations, but it can affect network convergence. In this work, we…

Machine Learning · Computer Science 2020-11-03 Md Aamir Raihan , Tor M. Aamodt

We study dropout in two-layer neural networks with rectified linear unit (ReLU) activations. Under mild overparametrization and assuming that the limiting kernel can separate the data distribution with a positive margin, we show that…

Machine Learning · Computer Science 2020-10-27 Poorya Mianjy , Raman Arora

Activation functions are fundamental to deep neural networks, governing gradient flow, optimization stability, and representational capacity. Within historic deep architectures, while ReLU has been the dominant choice for the activation…

Machine Learning · Computer Science 2026-03-10 Mingi Kang , Zai Yang , Jeova Farias Sales Rocha Neto

Activation functions can have a significant impact on reducing the topological complexity of input data and therefore improve the performance of the model. Selecting a suitable activation function is an essential step in neural model…

Computation and Language · Computer Science 2023-02-15 Haishuo Fang , Ji-Ung Lee , Nafise Sadat Moosavi , Iryna Gurevych
‹ Prev 1 8 9 10 Next ›