Search Results for author:
Found 12 papers, 3 papers with code
Approximate Thompson Sampling via Epistemic Neural Networks
Further, we demonstrate that the \textit{epinet} -- a small additive network that estimates uncertainty -- matches the performance of large ensembles at orders of magnitude lower computational cost.
The Neural Testbed: Evaluating Joint Predictions
Predictive distributions quantify uncertainties ignored by point estimates.
Evaluating Predictive Distributions: Does Bayesian Deep Learning Work?
This paper introduces \textit{The Neural Testbed}, which provides tools for the systematic evaluation of agents that generate such predictions.
From Predictions to Decisions: The Importance of Joint Predictive Distributions
A fundamental challenge for any intelligent system is prediction: given some inputs, can you predict corresponding outcomes?
Epistemic Neural Networks
We introduce the epinet: an architecture that can supplement any conventional neural network, including large pretrained models, and can be trained with modest incremental computation to estimate uncertainty.
Reinforcement Learning, Bit by Bit
To illustrate concepts, we design simple agents that build on them and present computational results that highlight data efficiency.
On Efficiency in Hierarchical Reinforcement Learning
Hierarchical Reinforcement Learning (HRL) approaches promise to provide more efficient solutions to sequential decision making problems, both in terms of statistical as well as computational efficiency.
Hypermodels for Exploration
This generalizes and extends the use of ensembles to approximate Thompson sampling.
Support Recovery for the Drift Coefficient of High-Dimensional Diffusions
Consider the problem of learning the drift coefficient of a $p$-dimensional stochastic differential equation from a sample path of length $T$.
Efficient Reinforcement Learning for High Dimensional Linear Quadratic Systems
In particular, our algorithm has an average cost of $(1+\eps)$ times the optimum cost after $T = \polylog(p) O(1/\eps^2)$.
Accelerated Time-of-Flight Mass Spectrometry
We study a simple modification to the conventional time of flight mass spectrometry (TOFMS) where a \emph{variable} and (pseudo)-\emph{random} pulsing rate is used which allows for traces from different pulses to overlap.
Learning Networks of Stochastic Differential Equations
We consider linear models for stochastic dynamics.
