English
Related papers

Related papers: General Bayesian Policy Learning

200 papers

We are motivated by the problem of learning policies for robotic systems with rich sensory inputs (e.g., vision) in a manner that allows us to guarantee generalization to environments unseen during training. We provide a framework for…

Robotics · Computer Science 2022-07-25 Abhinav Agarwal , Sushant Veer , Allen Z. Ren , Anirudha Majumdar

Policy learning algorithms are widely used in areas such as personalized medicine and advertising to develop individualized treatment regimes. However, most methods force a decision even when predictions are uncertain, which is risky in…

Machine Learning · Computer Science 2026-01-30 Ayush Sawarni , Jikai Jin , Justin Whitehouse , Vasilis Syrgkanis

Fully Bayesian approaches to sequential decision-making assume that problem parameters are generated from a known prior. In practice, such information is often lacking. This problem is exacerbated in setups with partial information, where a…

Machine Learning · Statistics 2022-08-08 Amit Peleg , Naama Pearl , Ron Meir

We study fair multi-objective reinforcement learning in which an agent must learn a policy that simultaneously achieves high reward on multiple dimensions of a vector-valued reward. Motivated by the fair resource allocation literature, we…

Computer Science and Game Theory · Computer Science 2024-02-09 Zimeng Fan , Nianli Peng , Muhang Tian , Brandon Fain

Bayesian models quantify uncertainty and facilitate optimal decision-making in downstream applications. For most models, however, practitioners are forced to use approximate inference techniques that lead to sub-optimal decisions due to…

Machine Learning · Statistics 2019-09-12 Tomasz Kuśmierczyk , Joseph Sakaya , Arto Klami

Transfer learning has received a lot of attention in the machine learning community over the last years, and several effective algorithms have been developed. However, relatively little is known about their theoretical properties,…

Machine Learning · Statistics 2014-05-13 Anastasia Pentina , Christoph H. Lampert

Bayesian optimisation is a popular technique for hyperparameter learning but typically requires initial exploration even in cases where similar prior tasks have been solved. We propose to transfer information across tasks using learnt…

Machine Learning · Statistics 2019-05-28 Ho Chung Leon Law , Peilin Zhao , Lucian Chan , Junzhou Huang , Dino Sejdinovic

Supervised learning has gone beyond the expected risk minimization framework. Central to most of these developments is the introduction of more general aggregation functions for losses incurred by the learner. In this paper, we turn towards…

Machine Learning · Computer Science 2024-06-05 Armando J. Cabrera Pacheco , Rabanus Derr , Robert C. Williamson

Contemporary machine learning methods will try to approach the Bayes error, as it is the lowest possible error any model can achieve. This paper postulates that any decision is composed of not one but two Bayesian decisions and that…

Machine Learning · Computer Science 2024-10-18 Stefan Jaeger

We formalize trust calibration for agentic tool use (deciding when an automated agent's proposed action may execute autonomously versus require human approval) as a preference-learning problem. A policy gateway maintains a Gaussian-process…

Artificial Intelligence · Computer Science 2026-05-20 Changkun Ou

The features in high dimensional biomedical prediction problems are often well described with lower dimensional manifolds. An example is genes that are organised in smaller functional networks. The outcome can then be described with the…

Bayesian persuasion, a central model in information design, studies how a sender, who privately observes a state drawn from a prior distribution, strategically sends a signal to influence a receiver's action. A key assumption is that both…

Computer Science and Game Theory · Computer Science 2025-05-23 Jingwu Tang , Jiahao Zhang , Fei Fang , Zhiwei Steven Wu

Bayesian optimization is a coherent, ubiquitous approach to decision-making under uncertainty, with applications including multi-arm bandits, active learning, and black-box optimization. Bayesian optimization selects decisions (i.e.…

Machine Learning · Computer Science 2023-12-13 Samuel Stanton , Wesley Maddox , Andrew Gordon Wilson

Traditionally Bayesian decision-theoretic design of experiments proceeds by choosing a design to minimise expectation of a given loss function over the space of all designs. The loss function encapsulates the aim of the experiment, and the…

Methodology · Statistics 2021-08-10 Antony M. Overstall , James M. McGree

The goal of this thesis is to develop the optimisation and generalisation theoretic foundations of learning in artificial neural networks. On optimisation, a new theoretical framework is proposed for deriving architecture-dependent…

Neural and Evolutionary Computing · Computer Science 2022-10-20 Jeremy Bernstein

Data point selection (DPS) is becoming a critical topic in deep learning due to the ease of acquiring uncurated training data compared to the difficulty of obtaining curated or processed data. Existing approaches to DPS are predominantly…

Machine Learning · Computer Science 2024-11-07 Xinnuo Xu , Minyoung Kim , Royson Lee , Brais Martinez , Timothy Hospedales

This paper introduces a loss-based generalized Bayesian methodology for high-dimensional robust regression with serially correlated errors and predictors. The proposed framework employs a novel scaled pseudo-Huber (SPH) loss function, which…

Methodology · Statistics 2025-03-13 Saptarshi Chakraborty , Kshitij Khare , George Michailidis

We present a PAC-Bayesian analysis of lifelong learning. In the lifelong learning problem, a sequence of learning tasks is observed one-at-a-time, and the goal is to transfer information acquired from previous tasks to new learning tasks.…

Machine Learning · Computer Science 2022-03-17 Hamish Flynn , David Reeb , Melih Kandemir , Jan Peters

We consider a Gaussian process formulation of the multiple kernel learning problem. The goal is to select the convex combination of kernel matrices that best explains the data and by doing so improve the generalisation on unseen data.…

Machine Learning · Statistics 2011-10-25 Cedric Archambeau , Francis Bach

The design of an experiment can be always be considered at least implicitly Bayesian, with prior knowledge used informally to aid decisions such as the variables to be studied and the choice of a plausible relationship between the…

Methodology · Statistics 2017-01-03 David C. Woods , Antony M. Overstall , Maria Adamou , Timothy W. Waite