Deriving Activation Functions Using Integration

• URL: http://arxiv.org/abs/2411.13010v3
• Date: Fri, 31 Jan 2025 19:28:05 GMT
• Title: Deriving Activation Functions Using Integration
• Authors: Allen Hao Huang, Imanol Schlag,
• Abstract summary: We introduce the Expanded Integral of the Exponential Linear Unit (xIELU), a trainable piecewise activation function derived by integrating trainable affine transformations. xIELU combines two key properties for the gradient: (1) a trainable and linearly increasing gradient for positive inputs, similar to Squared ReLU (ReLU$2$), and (2) a trainable gradient that can take negative values for negative inputs, inspired by Expanded SiLU (xSiLU) In experiments with 1.1B and 3B parameter Llama models trained on 125B tokens of FineWeb Edu, xIELU achieves lower
• Score: 8.345753173238956
• License:
• Abstract: Our work proposes a novel approach to designing activation functions by focusing on their gradients and deriving the corresponding activation functions using integration. We introduce the Expanded Integral of the Exponential Linear Unit (xIELU), a trainable piecewise activation function derived by integrating trainable affine transformations applied to the Exponential Linear Unit (ELU). xIELU combines two key properties for the gradient: (1) a trainable and linearly increasing gradient for positive inputs, similar to Squared ReLU (ReLU$^2$), and (2) a trainable gradient that can take negative values for negative inputs, inspired by Expanded SiLU (xSiLU). Conceptually, xIELU can be viewed as an extension of ReLU$^2$ to handle negative inputs. The trainable parameters in xIELU allow it to adaptively reduce its nonlinearity for higher-level representations deeper in the network. In experiments with 1.1B and 3B parameter Llama models trained on 125B tokens of FineWeb Edu, xIELU achieves lower perplexity compared to popular activation functions like ReLU$^2$ and SwiGLU when matched for the same compute cost and parameter count. A reference implementation is available at https://github.com/Anonymous5823/xielu.

Related papers

• Gompertz Linear Units: Leveraging Asymmetry for Enhanced Learning Dynamics [39.0860823332923]
  GoLU is a novel self-gated activation function defined as $mathrmGoLU(x) = x, mathrmGompertz(x)$, wheremathrmGompertz(x) = e-e-x$. GoLU's superior performance relative to state-of-the-art activation functions, highlights GoLU as a robust alternative to existing activation functions.
  arXiv  Detail & Related papers  (2025-02-05T22:32:22Z)
• Activation function optimization method: Learnable series linear units (LSLUs) [12.089173508371246]
  We propose a series-based learnable ac-tivation function called LSLU (Learnable Series Linear Units) This method simplifies deep learning networks while im-proving accuracy. We evaluate LSLU's performance on CIFAR10, CIFAR100, and specific task datasets (e.g., Silkworm)
  arXiv  Detail & Related papers  (2024-08-28T11:12:27Z)
• A Mean-Field Analysis of Neural Stochastic Gradient Descent-Ascent for Functional Minimax Optimization [90.87444114491116]
  This paper studies minimax optimization problems defined over infinite-dimensional function classes of overparametricized two-layer neural networks. We address (i) the convergence of the gradient descent-ascent algorithm and (ii) the representation learning of the neural networks. Results show that the feature representation induced by the neural networks is allowed to deviate from the initial one by the magnitude of $O(alpha-1)$, measured in terms of the Wasserstein distance.
  arXiv  Detail & Related papers  (2024-04-18T16:46:08Z)
• Stable Nonconvex-Nonconcave Training via Linear Interpolation [51.668052890249726]
  This paper presents a theoretical analysis of linearahead as a principled method for stabilizing (large-scale) neural network training. We argue that instabilities in the optimization process are often caused by the nonmonotonicity of the loss landscape and show how linear can help by leveraging the theory of nonexpansive operators.
  arXiv  Detail & Related papers  (2023-10-20T12:45:12Z)
• Parametric Leaky Tanh: A New Hybrid Activation Function for Deep Learning [0.0]
  Activation functions (AFs) are crucial components of deep neural networks (DNNs) We propose a novel hybrid activation function designed to combine the strengths of both the Tanh and Leaky ReLU activation functions. PLanh is differentiable at all points and addresses the 'dying ReLU' problem by ensuring a non-zero gradient for negative inputs.
  arXiv  Detail & Related papers  (2023-08-11T08:59:27Z)
• The Implicit Bias of Minima Stability in Multivariate Shallow ReLU Networks [53.95175206863992]
  We study the type of solutions to which gradient descent converges when used to train a single hidden-layer multivariate ReLU network with the quadratic loss. We prove that although shallow ReLU networks are universal approximators, stable shallow networks are not.
  arXiv  Detail & Related papers  (2023-06-30T09:17:39Z)
• TaLU: A Hybrid Activation Function Combining Tanh and Rectified Linear Unit to Enhance Neural Networks [1.3477333339913569]
  TaLU is a modified activation function combining Tanh and ReLU, which mitigates the dying gradient problem of ReLU. Deep learning model with the proposed activation function was tested on MNIST and CIFAR-10.
  arXiv  Detail & Related papers  (2023-05-08T01:13:59Z)
• Graph-adaptive Rectified Linear Unit for Graph Neural Networks [64.92221119723048]
  Graph Neural Networks (GNNs) have achieved remarkable success by extending traditional convolution to learning on non-Euclidean data. We propose Graph-adaptive Rectified Linear Unit (GReLU) which is a new parametric activation function incorporating the neighborhood information in a novel and efficient way. We conduct comprehensive experiments to show that our plug-and-play GReLU method is efficient and effective given different GNN backbones and various downstream tasks.
  arXiv  Detail & Related papers  (2022-02-13T10:54:59Z)
• Dynamic ReLU [74.973224160508]
  We propose dynamic ReLU (DY-ReLU), a dynamic input of parameters which are generated by a hyper function over all in-put elements. Compared to its static counterpart, DY-ReLU has negligible extra computational cost, but significantly more representation capability. By simply using DY-ReLU for MobileNetV2, the top-1 accuracy on ImageNet classification is boosted from 72.0% to 76.2% with only 5% additional FLOPs.
  arXiv  Detail & Related papers  (2020-03-22T23:45:35Z)
• Investigating the interaction between gradient-only line searches and different activation functions [0.0]
  Gradient-only line searches (GOLS) adaptively determine step sizes along search directions for discontinuous loss functions in neural network training. We find that GOLS are robust for a range of activation functions, but sensitive to the Rectified Linear Unit (ReLU) activation function in standard feedforward architectures.
  arXiv  Detail & Related papers  (2020-02-23T12:28:27Z)
• Gaussian Error Linear Units (GELUs) [58.195342948092964]
  We propose a neural network activation function that weights inputs by their value, rather than gates by their sign. We find performance improvements across all considered computer vision, natural language processing, and speech tasks.
  arXiv  Detail & Related papers  (2016-06-27T19:20:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.