Posterior Sampling via Autoregressive Generation

• URL: http://arxiv.org/abs/2405.19466v2
• Date: Tue, 08 Oct 2024 15:55:06 GMT
• Title: Posterior Sampling via Autoregressive Generation
• Authors: Kelly W Zhang, Tiffany Tianhui Cai, Hongseok Namkoong, Daniel Russo,
• Abstract summary: We propose a new framework for learning bandit algorithms from massive historical data. We use historical data to pretrain an autoregressive model to predict a sequence of repeated feedback/rewards. At decision-time, we autoregressively sample (impute) an imagined sequence of rewards for each action, and choose the action with the largest average imputed reward.
• Score: 11.713451719120707
• License:
• Abstract: Real-world decision-making requires grappling with a perpetual lack of data as environments change; intelligent agents must comprehend uncertainty and actively gather information to resolve it. We propose a new framework for learning bandit algorithms from massive historical data, which we demonstrate in a cold-start recommendation problem. First, we use historical data to pretrain an autoregressive model to predict a sequence of repeated feedback/rewards (e.g., responses to news articles shown to different users over time). In learning to make accurate predictions, the model implicitly learns an informed prior based on rich action features (e.g., article headlines) and how to sharpen beliefs as more rewards are gathered (e.g., clicks as each article is recommended). At decision-time, we autoregressively sample (impute) an imagined sequence of rewards for each action, and choose the action with the largest average imputed reward. Far from a heuristic, our approach is an implementation of Thompson sampling (with a learned prior), a prominent active exploration algorithm. We prove our pretraining loss directly controls online decision-making performance, and we demonstrate our framework on a news recommendation task where we integrate end-to-end fine-tuning of a pretrained language model to process news article headline text to improve performance.

Related papers

• Zero-shot Retrieval: Augmenting Pre-trained Models with Search Engines [83.65380507372483]
  Large pre-trained models can dramatically reduce the amount of task-specific data required to solve a problem, but they often fail to capture domain-specific nuances out of the box. This paper shows how to leverage recent advances in NLP and multi-modal learning to augment a pre-trained model with search engine retrieval.
  arXiv  Detail & Related papers  (2023-11-29T05:33:28Z)
• Overcoming Overconfidence for Active Learning [1.2776312584227847]
  We present two novel methods to address the problem of overconfidence that arises in the active learning scenario. The first is an augmentation strategy named Cross-Mix-and-Mix (CMaM), which aims to calibrate the model by expanding the limited training distribution. The second is a selection strategy named Ranked Margin Sampling (RankedMS), which prevents choosing data that leads to overly confident predictions.
  arXiv  Detail & Related papers  (2023-08-21T09:04:54Z)
• ASPEST: Bridging the Gap Between Active Learning and Selective Prediction [56.001808843574395]
  Selective prediction aims to learn a reliable model that abstains from making predictions when uncertain. Active learning aims to lower the overall labeling effort, and hence human dependence, by querying the most informative examples. In this work, we introduce a new learning paradigm, active selective prediction, which aims to query more informative samples from the shifted target domain.
  arXiv  Detail & Related papers  (2023-04-07T23:51:07Z)
• Meta-Wrapper: Differentiable Wrapping Operator for User Interest Selection in CTR Prediction [97.99938802797377]
  Click-through rate (CTR) prediction, whose goal is to predict the probability of the user to click on an item, has become increasingly significant in recommender systems. Recent deep learning models with the ability to automatically extract the user interest from his/her behaviors have achieved great success. We propose a novel approach under the framework of the wrapper method, which is named Meta-Wrapper.
  arXiv  Detail & Related papers  (2022-06-28T03:28:15Z)
• Optimizing Active Learning for Low Annotation Budgets [6.753808772846254]
  In deep learning, active learning is usually implemented as an iterative process in which successive deep models are updated via fine tuning. We tackle this issue by using an approach inspired by transfer learning. We introduce a novel acquisition function which exploits the iterative nature of AL process to select samples in a more robust fashion.
  arXiv  Detail & Related papers  (2022-01-18T18:53:10Z)
• Batch Reinforcement Learning from Crowds [24.717084423091865]
  A shortcoming of batch reinforcement learning is its requirement for rewards in data. Existing settings for lack of reward, such as behavioral cloning, rely on optimal demonstrations collected from humans. This paper addresses the lack of reward in a batch reinforcement learning setting by learning a reward function from preferences.
  arXiv  Detail & Related papers  (2021-11-08T05:46:33Z)
• Injecting Knowledge in Data-driven Vehicle Trajectory Predictors [82.91398970736391]
  Vehicle trajectory prediction tasks have been commonly tackled from two perspectives: knowledge-driven or data-driven. In this paper, we propose to learn a "Realistic Residual Block" (RRB) which effectively connects these two perspectives. Our proposed method outputs realistic predictions by confining the residual range and taking into account its uncertainty.
  arXiv  Detail & Related papers  (2021-03-08T16:03:09Z)
• Online Active Model Selection for Pre-trained Classifiers [72.84853880948894]
  We design an online selective sampling approach that actively selects informative examples to label and outputs the best model with high probability at any round. Our algorithm can be used for online prediction tasks for both adversarial and streams.
  arXiv  Detail & Related papers  (2020-10-19T19:53:15Z)
• Deep Bayesian Bandits: Exploring in Online Personalized Recommendations [4.845576821204241]
  We formulate a display advertising recommender as a contextual bandit. We implement exploration techniques that require sampling from the posterior distribution of click-through-rates. We test our proposed deep Bayesian bandits algorithm in the offline simulation and online AB setting.
  arXiv  Detail & Related papers  (2020-08-03T08:58:18Z)
• Value-driven Hindsight Modelling [68.658900923595]
  Value estimation is a critical component of the reinforcement learning (RL) paradigm. Model learning can make use of the rich transition structure present in sequences of observations, but this approach is usually not sensitive to the reward function. We develop an approach for representation learning in RL that sits in between these two extremes. This provides tractable prediction targets that are directly relevant for a task, and can thus accelerate learning the value function.
  arXiv  Detail & Related papers  (2020-02-19T18:10:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.