REVIEW 9 cited by
Variational Bayesian Last Layers
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Variational Bayesian Last Layers
read the original abstract
We introduce a deterministic variational formulation for training Bayesian last layer neural networks. This yields a sampling-free, single-pass model and loss that effectively improves uncertainty estimation. Our variational Bayesian last layer (VBLL) can be trained and evaluated with only quadratic complexity in last layer width, and is thus (nearly) computationally free to add to standard architectures. We experimentally investigate VBLLs, and show that they improve predictive accuracy, calibration, and out of distribution detection over baselines across both regression and classification. Finally, we investigate combining VBLL layers with variational Bayesian feature learning, yielding a lower variance collapsed variational inference method for Bayesian neural networks.
Forward citations
Cited by 9 Pith papers
-
A 65 nm Multi-Modal Bayesian Inference Engine with 16.3 fJ/Sample Calibration-Free GRNG for Risk-Aware At-Home Skin Lesion Screening
A 65 nm compute-in-memory multimodal Bayesian inference engine with calibration-free GRNG achieves 1.4x equal-risk coverage, >1.5x perturbation robustness, 5.5x process-variation resilience, and 1.8% higher balanced a...
-
General Incomplete Multimodal Learning via Dynamic Quality Perception
A unified multimodal learning framework models modality degradation as a continuous variable and uses a noise-aware quality estimator to adaptively weight fused representations under both intra- and inter-modality mis...
-
Refining Multidimensional Video Reward Models via Disentangled Influence Functions
Introduces dimension-disentangled influence estimation to prune or reweight training samples for MVRMs, outperforming global scalar filtering in alignment with ground truth.
-
Wahkon: A Statistically Principled Deep RKHS Superposition Network
Wahkon unifies Kolmogorov superposition with RKHS regularization to produce a deep network whose penalized estimator is exactly the MAP under a hierarchical GP prior and achieves minimax-optimal rates.
-
Self-Supervised Laplace Approximation for Bayesian Uncertainty Quantification
SSLA approximates the posterior predictive distribution by refitting Bayesian models on self-predicted data, providing a sampling-free method that improves predictive calibration over classical Laplace approximations ...
-
Self-Supervised Laplace Approximation for Bayesian Uncertainty Quantification
SSLA approximates the posterior predictive distribution by refitting Bayesian models on self-predicted data, yielding a deterministic uncertainty measure that outperforms standard Laplace approximations in calibration...
-
Efficient Bayesian Deep Ensembles via Analytic Predictive Inference
Independent neural predictors form a low-rank feature map that is aggregated by exact Bayesian linear regression, yielding a finite-rank Student-t process with competitive UCI regression performance.
-
A 65 nm Multi-Modal Bayesian Inference Engine with 16.3 fJ/Sample Calibration-Free GRNG for Risk-Aware At-Home Skin Lesion Screening
A 65 nm compute-in-memory chip implements multi-modal Bayesian neural networks with a calibration-free GRNG to deliver risk-aware skin lesion screening with reported gains in coverage, robustness, and efficiency over ...
-
Uncertainty-Calibrated Diffusion for Reliable 3D Molecular Graph Generation
UCD adjusts diffusion-based 3D molecular graph generation to handle epistemic uncertainty, improving sample quality and reaching new benchmark performance.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.