Sparse Uncertainty Representation in Deep Learning with Inducing Weights
arXiv:2105.14594
Abstract
Bayesian neural networks and deep ensembles represent two modern paradigms of uncertainty quantification in deep learning. Yet these approaches struggle to scale mainly due to memory inefficiency issues, since they require parameter storage several times higher than their deterministic counterparts. To address this, we augment the weight matrix of each layer with a small number of inducing weights, thereby projecting the uncertainty quantification into such low dimensional spaces. We further extend Matheron's conditional Gaussian sampling rule to enable fast weight sampling, which enables our inference method to maintain reasonable run-time as compared with ensembles. Importantly, our approach achieves competitive performance to the state-of-the-art in prediction and uncertainty estimation tasks with fully connected neural networks and ResNets, while reducing the parameter size to of that of a neural network.
arXiv commentNeurIPS 2021 camera ready
References in corpus (23)
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- Auto-Encoding Variational Bayes
- What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?
- The No-U-Turn Sampler: Adaptively Setting Path Lengths in Hamiltonian Monte Carlo
- On Calibration of Modern Neural Networks
- Weight Uncertainty in Neural Networks
- Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift
- SNIP: Single-shot Network Pruning based on Connection Sensitivity
- Deep Neural Networks as Gaussian Processes
- Markov Chain Monte Carlo and Variational Inference: Bridging the Gap
- Bayesian Compression for Deep Learning
- Multiplicative Normalizing Flows for Variational Bayesian Neural Networks
- Adversarial Examples, Uncertainty, and Transfer Testing Robustness in Gaussian Process Hybrid Deep Networks
- Functional Variational Bayesian Neural Networks
- Cyclical Stochastic Gradient MCMC for Bayesian Deep Learning
- BatchEnsemble: An Alternative Approach to Efficient Ensemble and Lifelong Learning
- 'In-Between' Uncertainty in Bayesian Neural Networks
- SLANG: Fast Structured Covariance Approximations for Bayesian Deep Learning with Natural Gradient
- The k-tied Normal Distribution: A Compact Parameterization of Gaussian Mean Field Posteriors in Bayesian Neural Networks
- Subspace Inference for Bayesian Deep Learning
- The Deep Weight Prior
- A Tutorial on Sparse Gaussian Processes and Variational Inference
- Bayesian Deep Learning via Subnetwork Inference