Search Results for author:
Found 11 papers, 5 papers with code
Efficient Exploration for LLMs
We present evidence of substantial benefit from efficient exploration in gathering human feedback to improve large language models.
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.
Fine-Tuning Language Models via Epistemic Neural Networks
Language models often pre-train on large unsupervised text corpora, then fine-tune on additional task-specific data.
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.
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.
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.
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.
Regret Bounds for Decentralized Learning in Cooperative Multi-Agent Dynamical Systems
This allows the agents to achieve a regret within $O(\sqrt{T})$ of the regret of the auxiliary single-agent problem.
Learning to Code: Coded Caching via Deep Reinforcement Learning
We consider a system comprising a file library and a network with a server and multiple users equipped with cache memories.
