Search Results for author:
Found 16 papers, 5 papers with code
RLHF and IIA: Perverse Incentives
Existing algorithms for reinforcement learning from human feedback (RLHF) can incentivize responses at odds with preferences because they are based on models that assume independence of irrelevant alternatives (IIA).
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.
Robustness of Epinets against Distributional Shifts
However, these improvements are relatively small compared to the outstanding issues in distributionally-robust deep learning.
Ensembles for Uncertainty Estimation: Benefits of Prior Functions and Bootstrapping
In machine learning, an agent needs to estimate uncertainty to efficiently explore and adapt and to make effective decisions.
An Analysis of Ensemble Sampling
Ensemble sampling serves as a practical approximation to Thompson sampling when maintaining an exact posterior distribution over model parameters is computationally intractable.
Evaluating High-Order Predictive Distributions in Deep Learning
Previous work has developed methods for assessing low-order predictive distributions with inputs sampled i. i. d.
Event-based Motion Segmentation by Cascaded Two-Level Multi-Model Fitting
In this paper, we present a cascaded two-level multi-model fitting method for identifying independently moving objects (i. e., the motion segmentation problem) with a monocular event camera.
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.
Event-based Motion Segmentation with Spatio-Temporal Graph Cuts
We develop a method to identify independently moving objects acquired with an event-based camera, i. e., to solve the event-based motion segmentation problem.
Hypermodels for Exploration
This generalizes and extends the use of ensembles to approximate Thompson sampling.
Information-Theoretic Confidence Bounds for Reinforcement Learning
We integrate information-theoretic concepts into the design and analysis of optimistic algorithms and Thompson sampling.
Ensemble Sampling
Thompson sampling has emerged as an effective heuristic for a broad range of online decision problems.
