Search Results for author:
Found 25 papers, 9 papers with code
Calibrating Bayesian UNet++ for Sub-Seasonal Forecasting
Seasonal forecasting is a crucial task when it comes to detecting the extreme heat and colds that occur due to climate change.
Probabilistic Actor-Critic: Learning to Explore with PAC-Bayes Uncertainty
We introduce Probabilistic Actor-Critic (PAC), a novel reinforcement learning algorithm with improved continuous control performance thanks to its ability to mitigate the exploration-exploitation trade-off.
Demystifying the Myths and Legends of Nonconvex Convergence of SGD
Additionally, our analyses allow us to measure the density of the $\epsilon$-stationary points in the final iterates of SGD, and we recover the classical $O(\frac{1}{\sqrt{T}})$ asymptotic rate under various existing assumptions on the objective function and the bounds on the stochastic gradient.
EdVAE: Mitigating Codebook Collapse with Evidential Discrete Variational Autoencoders
We evidentially monitor the significance of attaining the probability distribution over the codebook embeddings, in contrast to softmax usage.
Sampling-Free Probabilistic Deep State-Space Models
Many real-world dynamical systems can be described as State-Space Models (SSMs).
Estimation of Counterfactual Interventions under Uncertainties
This ambiguity is particularly challenging in continuous settings in which a continuum of explanations exist for the same observation.
BOF-UCB: A Bayesian-Optimistic Frequentist Algorithm for Non-Stationary Contextual Bandits
We propose a novel Bayesian-Optimistic Frequentist Upper Confidence Bound (BOF-UCB) algorithm for stochastic contextual linear bandits in non-stationary environments.
Cheap and Deterministic Inference for Deep State-Space Models of Interacting Dynamical Systems
Furthermore, we propose structured approximations to the covariance matrices of the Gaussian components in order to scale up to systems with many agents.
PAC-Bayesian Soft Actor-Critic Learning
Actor-critic algorithms address the dual goals of reinforcement learning (RL), policy evaluation and improvement, via two separate function approximators.
PAC-Bayes Bounds for Bandit Problems: A Survey and Experimental Comparison
On the one hand, we found that PAC-Bayes bounds are a useful tool for designing offline bandit algorithms with performance guarantees.
Learning Interacting Dynamical Systems with Latent Gaussian Process ODEs
We study time uncertainty-aware modeling of continuous-time dynamics of interacting objects.
PAC-Bayesian Lifelong Learning For Multi-Armed Bandits
We present a PAC-Bayesian analysis of lifelong learning.
Continual Learning of Multi-modal Dynamics with External Memory
We study the problem of fitting a model to a dynamical environment when new modes of behavior emerge sequentially.
Traversing Time with Multi-Resolution Gaussian Process State-Space Models
These models have a natural interpretation as discretized stochastic differential equations, but inference for long sequences with fast and slow transitions is difficult.
Inferring the Structure of Ordinary Differential Equations
Understanding physical phenomena oftentimes means understanding the underlying dynamical system that governs observational measurements.
Evidential Turing Processes
A probabilistic classifier with reliable predictive uncertainties i) fits successfully to the target domain data, ii) provides calibrated class probabilities in difficult regions of the target domain (e. g.\ class overlap), and iii) accurately identifies queries coming out of the target domain and rejects them.
Differentiable Implicit Layers
In this paper, we introduce an efficient backpropagation scheme for non-constrained implicit functions.
Learning Partially Known Stochastic Dynamics with Empirical PAC Bayes
Neural Stochastic Differential Equations model a dynamical environment with neural nets assigned to their drift and diffusion terms.
A Deterministic Approximation to Neural SDEs
Our deterministic approximation of the transition kernel is applicable to both training and prediction.
Differential Bayesian Neural Nets
Neural Ordinary Differential Equations (N-ODEs) are a powerful building block for learning systems, which extend residual networks to a continuous-time dynamical system.
Deep Active Learning with Adaptive Acquisition
As active learning is a scarce data regime, we bootstrap from a well-known heuristic that filters the bulk of data points on which all heuristics would agree, and learn a policy to warp the top portion of this ranking in the most beneficial way for the character of a specific data distribution.
Bayesian Evidential Deep Learning with PAC Regularization
We propose a novel method for closed-form predictive distribution modeling with neural nets.
Evidential Deep Learning to Quantify Classification Uncertainty
Deterministic neural nets have been shown to learn effective predictors on a wide range of machine learning problems.
Sampling-Free Variational Inference of Bayesian Neural Networks by Variance Backpropagation
We propose a new Bayesian Neural Net formulation that affords variational inference for which the evidence lower bound is analytically tractable subject to a tight approximation.
Variational Bayesian Multiple Instance Learning With Gaussian Processes
Gaussian Processes (GPs) are effective Bayesian predictors.
