Search Results for author:
Found 21 papers, 13 papers with code
A Sober Look at LLMs for Material Discovery: Are They Actually Good for Bayesian Optimization Over Molecules?
Bayesian optimization (BO) is an essential part of such workflows, enabling scientists to leverage prior domain knowledge into efficient exploration of a large molecular space.
Position Paper: Bayesian Deep Learning in the Age of Large-Scale AI
In the current landscape of deep learning research, there is a predominant emphasis on achieving high predictive accuracy in supervised tasks involving large image and language datasets.
Structured Inverse-Free Natural Gradient: Memory-Efficient & Numerically-Stable KFAC for Large Neural Nets
Second-order methods for deep learning -- such as KFAC -- can be useful for neural net training.
Preventing Arbitrarily High Confidence on Far-Away Data in Point-Estimated Discriminative Neural Networks
For instance, ReLU networks - a popular class of neural network architectures - have been shown to almost always yield high confidence predictions when the test data are far away from the training set, even when they are trained with OOD data.
On the Disconnect Between Theory and Practice of Overparametrized Neural Networks
Our empirical results demonstrate that this is not the case in optimization, uncertainty quantification or continual learning.
Promises and Pitfalls of the Linearized Laplace in Bayesian Optimization
The linearized-Laplace approximation (LLA) has been shown to be effective and efficient in constructing Bayesian neural networks.
Posterior Refinement Improves Sample Efficiency in Bayesian Neural Networks
We show that the resulting posterior approximation is competitive with even the gold-standard full-batch Hamiltonian Monte Carlo.
Discovering Inductive Bias with Gibbs Priors: A Diagnostic Tool for Approximate Bayesian Inference
By reframing the problem in terms of incompatible conditional distributions we arrive at a natural solution: the Gibbs prior.
Mixtures of Laplace Approximations for Improved Post-Hoc Uncertainty in Deep Learning
Deep neural networks are prone to overconfident predictions on outliers.
Laplace Redux -- Effortless Bayesian Deep Learning
Bayesian formulations of deep learning have been shown to have compelling theoretical properties and offer practical functional benefits, such as improved predictive uncertainty quantification and model selection.
Being a Bit Frequentist Improves Bayesian Neural Networks
Despite their compelling theoretical properties, Bayesian neural networks (BNNs) tend to perform worse than frequentist methods in classification-based uncertainty quantification (UQ) tasks such as out-of-distribution (OOD) detection.
Laplace Redux - Effortless Bayesian Deep Learning
Bayesian formulations of deep learning have been shown to have compelling theoretical properties and offer practical functional benefits, such as improved predictive uncertainty quantification and model selection.
An Infinite-Feature Extension for Bayesian ReLU Nets That Fixes Their Asymptotic Overconfidence
We extend finite ReLU BNNs with infinite ReLU features via the GP and show that the resulting model is asymptotically maximally uncertain far away from the data while the BNNs' predictive power is unaffected near the data.
Learnable Uncertainty under Laplace Approximations
Laplace approximations are classic, computationally lightweight means for constructing Bayesian neural networks (BNNs).
Fixing Asymptotic Uncertainty of Bayesian Neural Networks with Infinite ReLU Features
However, far away from the training data, even Bayesian neural networks (BNNs) can still underestimate uncertainty and thus be overconfident.
Fast Predictive Uncertainty for Classification with Bayesian Deep Networks
We reconsider old work (Laplace Bridge) to construct a Dirichlet approximation of this softmax output distribution, which yields an analytic map between Gaussian distributions in logit space and Dirichlet distributions (the conjugate prior to the Categorical distribution) in the output space.
Being Bayesian, Even Just a Bit, Fixes Overconfidence in ReLU Networks
These theoretical results validate the usage of last-layer Bayesian approximation and motivate a range of a fidelity-cost trade-off.
Compound Density Networks
Despite the huge success of deep neural networks (NNs), finding good mechanisms for quantifying their prediction uncertainty is still an open problem.
Predictive Uncertainty Quantification with Compound Density Networks
Despite the huge success of deep neural networks (NNs), finding good mechanisms for quantifying their prediction uncertainty is still an open problem.
Improving Response Selection in Multi-Turn Dialogue Systems by Incorporating Domain Knowledge
Building systems that can communicate with humans is a core problem in Artificial Intelligence.
Incorporating Literals into Knowledge Graph Embeddings
Most of the existing work on embedding (or latent feature) based knowledge graph analysis focuses mainly on the relations between entities.
