English
Related papers

Related papers: Stochastic activations

200 papers

Activation functions play a pivotal role in determining the training dynamics and neural network performance. The widely adopted activation function ReLU despite being simple and effective has few disadvantages including the Dying ReLU…

Machine Learning · Computer Science 2021-08-26 Sayan Nag , Mayukh Bhattacharyya

The efficacy of deep neural networks is heavily reliant on the design of non-linear activation functions, yet existing approaches often struggle to balance optimization stability with computational efficiency. While piecewise linear…

Artificial Intelligence · Computer Science 2026-05-05 Wentao Zhang , Yutong Zhang , Yifan Zhu , Wentao Mo

Fourier Analysis Network (FAN) was recently proposed as a simple way to improve neural network performance by replacing part of Rectified Linear Unit (ReLU) activations with sine and cosine functions. Although several studies have reported…

Machine Learning · Computer Science 2026-03-16 Sam Jeong , Hae Yong Kim

Many natural language processing applications use language models to generate text. These models are typically trained to predict the next word in a sequence, given the previous words and some context such as an image. However, at test time…

Machine Learning · Computer Science 2016-05-10 Marc'Aurelio Ranzato , Sumit Chopra , Michael Auli , Wojciech Zaremba

A pivotal aspect in the design of neural networks lies in selecting activation functions, crucial for introducing nonlinear structures that capture intricate input-output patterns. While the effectiveness of adaptive or trainable activation…

Machine Learning · Computer Science 2024-08-06 Farhad Pourkamali-Anaraki , Tahamina Nasrin , Robert E. Jensen , Amy M. Peterson , Christopher J. Hansen

This paper provides an analysis of state-of-the-art activation functions with respect to supervised classification of deep neural network. These activation functions comprise of Rectified Linear Units (ReLU), Exponential Linear Unit (ELU),…

Machine Learning · Computer Science 2021-04-07 Anh Nguyen , Khoa Pham , Dat Ngo , Thanh Ngo , Lam Pham

Large Language Models (LLMs) often generate inconsistent responses when prompted with semantically equivalent paraphrased inputs. Recently, activation steering, a technique that modulates LLMs' behaviours by adjusting their latent…

Computation and Language · Computer Science 2025-01-23 Jingyuan Yang , Rongjun Li , Weixuan Wang , Ziyu Zhou , Zhiyong Feng , Wei Peng

Neural architectures tend to fit their data with relatively simple functions. This "simplicity bias" is widely regarded as key to their success. This paper explores the limits of this principle. Building on recent findings that the…

Machine Learning · Computer Science 2025-03-14 Damien Teney , Liangze Jiang , Florin Gogianu , Ehsan Abbasnejad

Non-linear activation functions are crucial in Convolutional Neural Networks. However, until now they have not been well described in the frequency domain. In this work, we study the spectral behavior of ReLU, a popular activation function.…

Machine Learning · Computer Science 2025-05-13 Christodoulos Kechris , Jonathan Dan , Jose Miranda , David Atienza

We consider functions from the real numbers to the real numbers, output by a neural network with 1 hidden activation layer, arbitrary width, and ReLU activation function. We assume that the parameters of the neural network are chosen…

Machine Learning · Computer Science 2023-04-20 David Holmes

Activation functions play an important role in training artificial neural networks. The majority of currently used activation functions are deterministic in nature, with their fixed input-output relationship. In this work, we propose a…

Element-wise activation functions play a critical role in deep neural networks via affecting the expressivity power and the learning dynamics. Learning-based activation functions have recently gained increasing attention and success. We…

Machine Learning · Computer Science 2020-10-05 Dengsheng Chen , Jun Li , Kai Xu

In this work, we develop analysis and algorithms for a class of (stochastic) bilevel optimization problems whose lower-level (LL) problem is strongly convex and linearly constrained. Most existing approaches for solving such problems rely…

Optimization and Control · Mathematics 2025-04-08 Prashant Khanduri , Ioannis Tsaknakis , Yihua Zhang , Sijia Liu , Mingyi Hong

This paper introduces scalable, sampling-based algorithms that optimize trained neural networks with ReLU activations. We first propose an iterative algorithm that takes advantage of the piecewise linear structure of ReLU neural networks…

Optimization and Control · Mathematics 2022-06-07 Georgia Perakis , Asterios Tsiourvas

We prove a large deviation principle for deep neural networks with Gaussian weights and at most linearly growing activation functions, such as ReLU. This generalises earlier work, in which bounded and continuous activation functions were…

Machine Learning · Statistics 2026-02-10 Quirin Vogel

A proper initialization of the weights in a neural network is critical to its convergence. Current insights into weight initialization come primarily from linear activation functions. In this paper, I develop a theory for weight…

Machine Learning · Computer Science 2017-05-04 Siddharth Krishna Kumar

The large number of ReLU non-linearity operations in existing deep neural networks makes them ill-suited for latency-efficient private inference (PI). Existing techniques to reduce ReLU operations often involve manual effort and sacrifice…

Computer Vision and Pattern Recognition · Computer Science 2023-01-24 Souvik Kundu , Shunlin Lu , Yuke Zhang , Jacqueline Liu , Peter A. Beerel

Activation function has a significant impact on the dynamics, convergence, and performance of deep neural networks. The search for a consistent and high-performing activation function has always been a pursuit during deep learning model…

Computer Vision and Pattern Recognition · Computer Science 2024-09-17 Abdur Rahman , Lu He , Haifeng Wang

Dynamic activation (DA) techniques, such as DejaVu and MoEfication, have demonstrated their potential to significantly enhance the inference efficiency of large language models (LLMs). However, these techniques often rely on ReLU activation…

Computation and Language · Computer Science 2024-08-22 Chi Ma , Mincong Huang , Ying Zhang , Chao Wang , Yujie Wang , Lei Yu , Chuan Liu , Wei Lin

The simultaneous rise of machine learning as a service and concerns over user privacy have increasingly motivated the need for private inference (PI). While recent work demonstrates PI is possible using cryptographic primitives, the…

Machine Learning · Computer Science 2021-06-17 Zahra Ghodsi , Nandan Kumar Jha , Brandon Reagen , Siddharth Garg
‹ Prev 1 4 5 6 7 8 10 Next ›