A Unified Model and Dimension for Interactive Estimation

• URL: http://arxiv.org/abs/2306.06184v1
• Date: Fri, 9 Jun 2023 18:21:04 GMT
• Title: A Unified Model and Dimension for Interactive Estimation
• Authors: Nataly Brukhim, Miroslav Dudik, Aldo Pacchiano, Robert Schapire
• Abstract summary: We introduce a measure called dissimilarity dimension which largely captures learnability in our model. We show that our framework subsumes and unifies two classic learning models: statistical-query learning and structured bandits.
• Score: 20.39351301232109
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We study an abstract framework for interactive learning called interactive estimation in which the goal is to estimate a target from its "similarity'' to points queried by the learner. We introduce a combinatorial measure called dissimilarity dimension which largely captures learnability in our model. We present a simple, general, and broadly-applicable algorithm, for which we obtain both regret and PAC generalization bounds that are polynomial in the new dimension. We show that our framework subsumes and thereby unifies two classic learning models: statistical-query learning and structured bandits. We also delineate how the dissimilarity dimension is related to well-known parameters for both frameworks, in some cases yielding significantly improved analyses.

Related papers

• Modern Neighborhood Components Analysis: A Deep Tabular Baseline Two Decades Later [59.88557193062348]
  We revisit the classic Neighborhood Component Analysis (NCA), designed to learn a linear projection that captures semantic similarities between instances. We find that minor modifications, such as adjustments to the learning objectives and the integration of deep learning architectures, significantly enhance NCA's performance. We also introduce a neighbor sampling strategy that improves both the efficiency and predictive accuracy of our proposed ModernNCA.
  arXiv  Detail & Related papers  (2024-07-03T16:38:57Z)
• Multi-Dimensional Optimization for Text Summarization via Reinforcement Learning [12.083649916114402]
  We propose multi-objective reinforcement learning tailored to generate balanced summaries across all four dimensions. Unlike prior ROUGE-based rewards relying on reference summaries, we use a QA-based reward model that aligns with human preferences. Our approach achieved substantial performance gains compared to baseline models on representative summarization datasets.
  arXiv  Detail & Related papers  (2024-06-01T05:15:12Z)
• Syntax-Informed Interactive Model for Comprehensive Aspect-Based Sentiment Analysis [0.0]
  We introduce an innovative model: Syntactic Dependency Enhanced Multi-Task Interaction Architecture (SDEMTIA) for comprehensive ABSA. Our approach innovatively exploits syntactic knowledge (dependency relations and types) using a specialized Syntactic Dependency Embedded Interactive Network (SDEIN) We also incorporate a novel and efficient message-passing mechanism within a multi-task learning framework to bolster learning efficacy.
  arXiv  Detail & Related papers  (2023-11-28T16:03:22Z)
• Variable Importance Matching for Causal Inference [73.25504313552516]
  We describe a general framework called Model-to-Match that achieves these goals. Model-to-Match uses variable importance measurements to construct a distance metric. We operationalize the Model-to-Match framework with LASSO.
  arXiv  Detail & Related papers  (2023-02-23T00:43:03Z)
• Symphony in the Latent Space: Provably Integrating High-dimensional Techniques with Non-linear Machine Learning Models [19.824998167546298]
  This paper revisits building machine learning algorithms that involve interactions between entities. We show that it is possible to decouple the learning of high-dimensional interactions from the learning of non-linear feature interactions.
  arXiv  Detail & Related papers  (2022-12-01T20:18:26Z)
• A General Framework for Sample-Efficient Function Approximation in Reinforcement Learning [132.45959478064736]
  We propose a general framework that unifies model-based and model-free reinforcement learning. We propose a novel estimation function with decomposable structural properties for optimization-based exploration. Under our framework, a new sample-efficient algorithm namely OPtimization-based ExploRation with Approximation (OPERA) is proposed.
  arXiv  Detail & Related papers  (2022-09-30T17:59:16Z)
• Unified Algorithms for RL with Decision-Estimation Coefficients: PAC, Reward-Free, Preference-Based Learning, and Beyond [28.118197762236953]
  We develop a unified algorithm framework for a large class of learning goals. Our framework handles many learning goals such as no-regret RL, PAC RL, reward-free learning, model estimation, and preference-based learning. As applications, we propose "decouplable representation" as a natural sufficient condition for bounding generalized DECs.
  arXiv  Detail & Related papers  (2022-09-23T17:47:24Z)
• Federated Learning Aggregation: New Robust Algorithms with Guarantees [63.96013144017572]
  Federated learning has been recently proposed for distributed model training at the edge. This paper presents a complete general mathematical convergence analysis to evaluate aggregation strategies in a federated learning framework. We derive novel aggregation algorithms which are able to modify their model architecture by differentiating client contributions according to the value of their losses.
  arXiv  Detail & Related papers  (2022-05-22T16:37:53Z)
• Deep Relational Metric Learning [84.95793654872399]
  This paper presents a deep relational metric learning framework for image clustering and retrieval. We learn an ensemble of features that characterizes an image from different aspects to model both interclass and intraclass distributions. Experiments on the widely-used CUB-200-2011, Cars196, and Stanford Online Products datasets demonstrate that our framework improves existing deep metric learning methods and achieves very competitive results.
  arXiv  Detail & Related papers  (2021-08-23T09:31:18Z)
• Dialogue Response Selection with Hierarchical Curriculum Learning [52.3318584971562]
  We study the learning of a matching model for dialogue response selection. Motivated by the recent finding that random negatives are often too trivial to train a reliable model, we propose a hierarchical curriculum learning framework.
  arXiv  Detail & Related papers  (2020-12-29T14:06:41Z)

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.