English
Related papers

Related papers: Model-based RL with Optimistic Posterior Sampling:…

200 papers

We present a new algorithm based on posterior sampling for learning in Constrained Markov Decision Processes (CMDP) in the infinite-horizon undiscounted setting. The algorithm achieves near-optimal regret bounds while being advantageous…

Machine Learning · Computer Science 2024-05-30 Danil Provodin , Maurits Kaptein , Mykola Pechenizkiy

We propose a practical non-episodic PSRL algorithm that unlike recent state-of-the-art PSRL algorithms uses a deterministic, model-independent episode switching schedule. Our algorithm termed deterministic schedule PSRL (DS-PSRL) is…

Machine Learning · Computer Science 2018-10-24 Georgios Theocharous , Zheng Wen , Yasin Abbasi-Yadkori , Nikos Vlassis

We are interested in the problem of robust parametric estimation of a density from $n$ i.i.d. observations. By using a practice-oriented procedure based on robust tests, we build an estimator for which we establish non-asymptotic risk…

Statistics Theory · Mathematics 2016-03-31 Mathieu Sart

We present a new algorithm based on posterior sampling for learning in constrained Markov decision processes (CMDP) in the infinite-horizon undiscounted setting. The algorithm achieves near-optimal regret bounds while being advantageous…

Machine Learning · Computer Science 2023-09-28 Danil Provodin , Pratik Gajane , Mykola Pechenizkiy , Maurits Kaptein

Impressive results in natural language processing (NLP) based on the Transformer neural network architecture have inspired researchers to explore viewing offline reinforcement learning (RL) as a generic sequence modeling problem. Recent…

Machine Learning · Computer Science 2022-07-22 Adam Villaflor , Zhe Huang , Swapnil Pande , John Dolan , Jeff Schneider

We present a powerful general framework for designing data-dependent optimization algorithms, building upon and unifying recent techniques in adaptive regularization, optimistic gradient predictions, and problem-dependent randomization. We…

Machine Learning · Statistics 2015-10-14 Mehryar Mohri , Scott Yang

We consider the problem of estimating the joint distribution $P$ of $n$ independent random variables within the Bayes paradigm from a non-asymptotic point of view. Assuming that $P$ admits some density $s$ with respect to a given reference…

Statistics Theory · Mathematics 2020-03-30 Yannick Baraud , Lucien Birgé

Given a noisy linear measurement $y = Ax + \xi$ of a distribution $p(x)$, and a good approximation to the prior $p(x)$, when can we sample from the posterior $p(x \mid y)$? Posterior sampling provides an accurate and fair framework for…

Machine Learning · Computer Science 2025-11-19 Zhiyang Xun , Shivam Gupta , Eric Price

Many models in natural language processing define probabilistic distributions over linguistic structures. We argue that (1) the quality of a model' s posterior distribution can and should be directly evaluated, as to whether probabilities…

Computation and Language · Computer Science 2015-09-03 Khanh Nguyen , Brendan O'Connor

Recently, much work has been done on extending the scope of online learning and incremental stochastic optimization algorithms. In this paper we contribute to this effort in two ways: First, based on a new regret decomposition and a…

Machine Learning · Computer Science 2017-09-12 Pooria Joulani , András György , Csaba Szepesvári

This paper addresses the task of estimating a covariance matrix under a patternless sparsity assumption. In contrast to existing approaches based on thresholding or shrinkage penalties, we propose a likelihood-based method that regularizes…

Methodology · Statistics 2021-09-13 Jason Xu , Kenneth Lange

We present an algorithm based on posterior sampling (aka Thompson sampling) that achieves near-optimal worst-case regret bounds when the underlying Markov Decision Process (MDP) is communicating with a finite, though unknown, diameter. Our…

Machine Learning · Computer Science 2020-04-01 Shipra Agrawal , Randy Jia

Autoregressive models (ARMs) currently hold state-of-the-art performance in likelihood-based modeling of image and audio data. Generally, neural network based ARMs are designed to allow fast inference, but sampling from these models is…

Machine Learning · Computer Science 2020-07-09 Auke Wiggers , Emiel Hoogeboom

In statistics and machine learning, logistic regression is a widely-used supervised learning technique primarily employed for binary classification tasks. When the number of observations greatly exceeds the number of predictor variables, we…

Machine Learning · Statistics 2024-04-02 Agniva Chowdhury , Pradeep Ramuhalli

In this paper, we develop a simulation-based framework for regularized logistic regression, exploiting two novel results for scale mixtures of normals. By carefully choosing a hierarchical model for the likelihood by one type of mixture,…

Methodology · Statistics 2015-03-17 Robert B. Gramacy , Nicholas G. Polson

In the context of state-space models, skeleton-based smoothing algorithms rely on a backward sampling step which by default has a $\mathcal O(N^2)$ complexity (where $N$ is the number of particles). Existing improvements in the literature…

Computation · Statistics 2023-03-08 Hai-Dang Dau , Nicolas Chopin

Likelihood-free methods are an essential tool for performing inference for implicit models which can be simulated from, but for which the corresponding likelihood is intractable. However, common likelihood-free methods do not scale well to…

Methodology · Statistics 2022-07-15 Christopher Drovandi , David J Nott , David T Frazier

A useful sampling-reconstruction model should be stable with respect to different kind of small perturbations, regardless whether they result from jitter, measurement errors, or simply from a small change in the model assumptions. In this…

General Mathematics · Mathematics 2007-05-31 E. costa-Reyes , A. Aldroubi , I. Krishtal

We present a randomized maximum a posteriori (rMAP) method for generating approximate samples of posteriors in high dimensional Bayesian inverse problems governed by large-scale forward problems. We derive the rMAP approach by: 1) casting…

Computation · Statistics 2016-02-12 Kainan Wang , Tan Bui-Thanh , Omar Ghattas

In many domains, scientists build complex simulators of natural phenomena that encode their hypotheses about the underlying processes. These simulators can be deterministic or stochastic, fast or slow, constrained or unconstrained, and so…

Machine Learning · Statistics 2014-12-10 Edward Meeds , Michael Chiang , Mary Lee , Olivier Cinquin , John Lowengrub , Max Welling