no code implementations • 2 Dec 2023 • Wanqiao Xu, Shi Dong, Xiuyuan Lu, Grace Lam, Zheng Wen, Benjamin Van Roy
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).
1 code implementation • 18 Feb 2023 • Ian Osband, Zheng Wen, Seyed Mohammad Asghari, Vikranth Dwaracherla, Morteza Ibrahimi, Xiuyuan Lu, Benjamin Van Roy
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.
no code implementations • 1 Jul 2022 • Xiuyuan Lu, Ian Osband, Seyed Mohammad Asghari, Sven Gowal, Vikranth Dwaracherla, Zheng Wen, Benjamin Van Roy
However, these improvements are relatively small compared to the outstanding issues in distributionally-robust deep learning.
no code implementations • 8 Jun 2022 • Vikranth Dwaracherla, Zheng Wen, Ian Osband, Xiuyuan Lu, Seyed Mohammad Asghari, Benjamin Van Roy
In machine learning, an agent needs to estimate uncertainty to efficiently explore and adapt and to make effective decisions.
no code implementations • 2 Mar 2022 • Chao Qin, Zheng Wen, Xiuyuan Lu, Benjamin Van Roy
Ensemble sampling serves as a practical approximation to Thompson sampling when maintaining an exact posterior distribution over model parameters is computationally intractable.
1 code implementation • 28 Feb 2022 • Ian Osband, Zheng Wen, Seyed Mohammad Asghari, Vikranth Dwaracherla, Xiuyuan Lu, Benjamin Van Roy
Previous work has developed methods for assessing low-order predictive distributions with inputs sampled i. i. d.
no code implementations • 5 Nov 2021 • Xiuyuan Lu, Yi Zhou, Shaojie Shen
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.
1 code implementation • 9 Oct 2021 • Ian Osband, Zheng Wen, Seyed Mohammad Asghari, Vikranth Dwaracherla, Botao Hao, Morteza Ibrahimi, Dieterich Lawson, Xiuyuan Lu, Brendan O'Donoghue, Benjamin Van Roy
Predictive distributions quantify uncertainties ignored by point estimates.
no code implementations • 29 Sep 2021 • Ian Osband, Zheng Wen, Seyed Mohammad Asghari, Xiuyuan Lu, Morteza Ibrahimi, Vikranth Dwaracherla, Dieterich Lawson, Brendan O'Donoghue, Botao Hao, Benjamin Van Roy
This paper introduces \textit{The Neural Testbed}, which provides tools for the systematic evaluation of agents that generate such predictions.
no code implementations • 20 Jul 2021 • Zheng Wen, Ian Osband, Chao Qin, Xiuyuan Lu, Morteza Ibrahimi, Vikranth Dwaracherla, Mohammad Asghari, Benjamin Van Roy
A fundamental challenge for any intelligent system is prediction: given some inputs, can you predict corresponding outcomes?
1 code implementation • NeurIPS 2023 • Ian Osband, Zheng Wen, Seyed Mohammad Asghari, Vikranth Dwaracherla, Morteza Ibrahimi, Xiuyuan Lu, Benjamin Van Roy
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.
no code implementations • 6 Mar 2021 • Xiuyuan Lu, Benjamin Van Roy, Vikranth Dwaracherla, Morteza Ibrahimi, Ian Osband, Zheng Wen
To illustrate concepts, we design simple agents that build on them and present computational results that highlight data efficiency.
1 code implementation • 16 Dec 2020 • Yi Zhou, Guillermo Gallego, Xiuyuan Lu, SiQi Liu, Shaojie Shen
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.
no code implementations • ICLR 2020 • Vikranth Dwaracherla, Xiuyuan Lu, Morteza Ibrahimi, Ian Osband, Zheng Wen, Benjamin Van Roy
This generalizes and extends the use of ensembles to approximate Thompson sampling.
no code implementations • NeurIPS 2019 • Xiuyuan Lu, Benjamin Van Roy
We integrate information-theoretic concepts into the design and analysis of optimistic algorithms and Thompson sampling.
no code implementations • NeurIPS 2017 • Xiuyuan Lu, Benjamin Van Roy
Thompson sampling has emerged as an effective heuristic for a broad range of online decision problems.