Hi-fi functional priors by learning activations

• URL: http://arxiv.org/abs/2508.08880v1
• Date: Tue, 12 Aug 2025 12:09:22 GMT
• Title: Hi-fi functional priors by learning activations
• Authors: Marcin Sendera, Amin Sorkhei, Tomasz Kuśmierczyk,
• Abstract summary: We explore how trainable activations can accommodate higher-complexity priors and match intricate target function distributions.<n>Our empirical findings indicate that even BNNs with a single wide hidden layer when equipped with flexible trainable activation, can effectively achieve desired function-space priors.
• Score: 1.0468715529145969
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Function-space priors in Bayesian Neural Networks (BNNs) provide a more intuitive approach to embedding beliefs directly into the model's output, thereby enhancing regularization, uncertainty quantification, and risk-aware decision-making. However, imposing function-space priors on BNNs is challenging. We address this task through optimization techniques that explore how trainable activations can accommodate higher-complexity priors and match intricate target function distributions. We investigate flexible activation models, including Pade functions and piecewise linear functions, and discuss the learning challenges related to identifiability, loss construction, and symmetries. Our empirical findings indicate that even BNNs with a single wide hidden layer when equipped with flexible trainable activation, can effectively achieve desired function-space priors.

Related papers

• Deep Hierarchical Learning with Nested Subspace Networks [53.71337604556311]
  We propose Nested Subspace Networks (NSNs) for large neural networks.<n>NSNs enable a single model to be dynamically and granularly adjusted across a continuous spectrum of compute budgets.<n>We show that NSNs can be surgically applied to pre-trained LLMs and unlock a smooth and predictable compute-performance frontier.
  arXiv  Detail & Related papers  (2025-09-22T15:13:14Z)
• Revisiting the Equivalence of Bayesian Neural Networks and Gaussian Processes: On the Importance of Learning Activations [1.0468715529145969]
  We show that trainable activations are crucial for effective mapping of GP priors to wide BNNs.<n>We also introduce trainable periodic activations that ensure global stationarity by design.
  arXiv  Detail & Related papers  (2024-10-21T08:42:10Z)
• Empowering Bayesian Neural Networks with Functional Priors through Anchored Ensembling for Mechanics Surrogate Modeling Applications [0.0]
  We present a novel BNN training scheme based on anchored ensembling that can integrate a priori information available in the function space. The anchoring scheme makes use of low-rank correlations between NN parameters, learnt from pre-training to realizations of the functional prior. We also perform a study to demonstrate how correlations between NN weights, which are often neglected in existing BNN implementations, is critical to appropriately transfer knowledge between the function-space and parameter-space priors.
  arXiv  Detail & Related papers  (2024-09-08T22:27:50Z)
• Adaptive Activation Functions for Predictive Modeling with Sparse Experimental Data [2.012425476229879]
  This study investigates the influence of adaptive or trainable activation functions on classification accuracy and predictive uncertainty in settings characterized by limited data availability. Our investigation reveals that adaptive activation functions, such as Exponential Linear Unit (ELU) and Softplus, with individual trainable parameters, result in accurate and confident prediction models.
  arXiv  Detail & Related papers  (2024-02-08T04:35:09Z)
• Continual Learning via Sequential Function-Space Variational Inference [65.96686740015902]
  We propose an objective derived by formulating continual learning as sequential function-space variational inference. Compared to objectives that directly regularize neural network predictions, the proposed objective allows for more flexible variational distributions. We demonstrate that, across a range of task sequences, neural networks trained via sequential function-space variational inference achieve better predictive accuracy than networks trained with related methods.
  arXiv  Detail & Related papers  (2023-12-28T18:44:32Z)
• Learning Specialized Activation Functions for Physics-informed Neural Networks [36.823376881651]
  Physics-informed neural networks (PINNs) are known to suffer from optimization difficulty. We show that PINNs exhibit high sensitivity to activation functions when solving PDEs with distinct properties. We introduce adaptive activation functions to search for the optimal function when solving different problems.
  arXiv  Detail & Related papers  (2023-08-08T06:11:52Z)
• Promises and Pitfalls of the Linearized Laplace in Bayesian Optimization [73.80101701431103]
  The linearized-Laplace approximation (LLA) has been shown to be effective and efficient in constructing Bayesian neural networks. We study the usefulness of the LLA in Bayesian optimization and highlight its strong performance and flexibility.
  arXiv  Detail & Related papers  (2023-04-17T14:23:43Z)
• Offline Reinforcement Learning with Differentiable Function Approximation is Provably Efficient [65.08966446962845]
  offline reinforcement learning, which aims at optimizing decision-making strategies with historical data, has been extensively applied in real-life applications. We take a step by considering offline reinforcement learning with differentiable function class approximation (DFA) Most importantly, we show offline differentiable function approximation is provably efficient by analyzing the pessimistic fitted Q-learning algorithm.
  arXiv  Detail & Related papers  (2022-10-03T07:59:42Z)
• Exploring Linear Feature Disentanglement For Neural Networks [63.20827189693117]
  Non-linear activation functions, e.g., Sigmoid, ReLU, and Tanh, have achieved great success in neural networks (NNs) Due to the complex non-linear characteristic of samples, the objective of those activation functions is to project samples from their original feature space to a linear separable feature space. This phenomenon ignites our interest in exploring whether all features need to be transformed by all non-linear functions in current typical NNs.
  arXiv  Detail & Related papers  (2022-03-22T13:09:17Z)
• Gone Fishing: Neural Active Learning with Fisher Embeddings [55.08537975896764]
  There is an increasing need for active learning algorithms that are compatible with deep neural networks. This article introduces BAIT, a practical representation of tractable, and high-performing active learning algorithm for neural networks.
  arXiv  Detail & Related papers  (2021-06-17T17:26:31Z)
• Activation function design for deep networks: linearity and effective initialisation [10.108857371774977]
  We study how to avoid two problems at initialisation identified in prior works. We prove that both these problems can be avoided by choosing an activation function possessing a sufficiently large linear region around the origin.
  arXiv  Detail & Related papers  (2021-05-17T11:30:46Z)

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.